Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 584 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2436. Min Range: -8.2436
Max Act: 8.2436. Min Act: -0.1700
Data Index: 4623241 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2436. Min Range: -8.2436
Max Act: 8.2436. Min Act: -0.1700
Data Index: 8010713 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2436. Min Range: -8.2436
Max Act: 8.1811. Min Act: -0.1700
Data Index: 3653803 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2436. Min Range: -8.2436
Max Act: 8.0874. Min Act: -0.1700
Data Index: 6542441 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2436. Min Range: -8.2436
Max Act: 7.9624. Min Act: -0.1700
Data Index: 4227816 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2436. Min Range: -8.2436
Max Act: 7.9936. Min Act: -0.1700
Data Index: 5737001 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2436. Min Range: -8.2436
Max Act: 7.9311. Min Act: -0.1700
Data Index: 5201630 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2436. Min Range: -8.2436
Max Act: 7.8999. Min Act: -0.1700
Data Index: 5294728 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2436. Min Range: -8.2436
Max Act: 7.8999. Min Act: -0.1700
Data Index: 3941750 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2436. Min Range: -8.2436
Max Act: 7.8686. Min Act: -0.1700
Data Index: 5968925 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2436. Min Range: -8.2436
Max Act: 7.7749. Min Act: -0.1700
Data Index: 7998848 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2436. Min Range: -8.2436
Max Act: 7.7749. Min Act: -0.1700
Data Index: 8696875 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2436. Min Range: -8.2436
Max Act: 7.7749. Min Act: -0.1700
Data Index: 5525804 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2436. Min Range: -8.2436
Max Act: 7.7436. Min Act: -0.1700
Data Index: 6730626 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2436. Min Range: -8.2436
Max Act: 7.7124. Min Act: -0.1700
Data Index: 1905544 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2436. Min Range: -8.2436
Max Act: 7.7436. Min Act: -0.1700
Data Index: 4857516 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2436. Min Range: -8.2436
Max Act: 7.6811. Min Act: -0.1700
Data Index: 8497834 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2436. Min Range: -8.2436
Max Act: 7.6811. Min Act: -0.1700
Data Index: 8580838 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2436. Min Range: -8.2436
Max Act: 7.6811. Min Act: -0.1700
Data Index: 2040901 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2436. Min Range: -8.2436
Max Act: 7.6499. Min Act: -0.1700
Data Index: 113439 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19