Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 778 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.0628. Min Range: -11.0628
Max Act: 11.0628. Min Act: -0.1700
Data Index: 7473382 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.9378. Min Act: -0.1700
Data Index: 8003785 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.8753. Min Act: -0.1700
Data Index: 6483699 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.7503. Min Act: -0.1700
Data Index: 622112 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.7503. Min Act: -0.1700
Data Index: 6619509 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.7503. Min Act: -0.1700
Data Index: 1495830 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.6878. Min Act: -0.1700
Data Index: 6632675 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.6878. Min Act: -0.1700
Data Index: 8003803 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.5003. Min Act: -0.1700
Data Index: 2825347 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.5628. Min Act: -0.1700
Data Index: 1384407 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.4378. Min Act: -0.1700
Data Index: 3307551 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.5003. Min Act: -0.1700
Data Index: 4189986 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.5003. Min Act: -0.1700
Data Index: 7819981 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.5628. Min Act: -0.1700
Data Index: 6033623 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.4378. Min Act: -0.1700
Data Index: 5358201 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.4378. Min Act: -0.1700
Data Index: 6185755 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.3753. Min Act: -0.1700
Data Index: 8003794 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.4378. Min Act: -0.1700
Data Index: 4881204 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.4378. Min Act: -0.1700
Data Index: 3820773 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0628. Min Range: -11.0628
Max Act: 10.3128. Min Act: -0.1700
Data Index: 6154095 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19