Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2636 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4819. Min Range: -7.4819
Max Act: 7.4819. Min Act: -0.1700
Data Index: 8169648 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4819. Min Range: -7.4819
Max Act: 7.1694. Min Act: -0.1700
Data Index: 7685295 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4819. Min Range: -7.4819
Max Act: 7.1382. Min Act: -0.1700
Data Index: 1917961 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4819. Min Range: -7.4819
Max Act: 7.0757. Min Act: -0.1700
Data Index: 4365570 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4819. Min Range: -7.4819
Max Act: 6.9194. Min Act: -0.1700
Data Index: 537690 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4819. Min Range: -7.4819
Max Act: 6.8569. Min Act: -0.1700
Data Index: 7550259 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4819. Min Range: -7.4819
Max Act: 6.8257. Min Act: -0.1700
Data Index: 7759766 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4819. Min Range: -7.4819
Max Act: 6.7319. Min Act: -0.1700
Data Index: 5369616 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4819. Min Range: -7.4819
Max Act: 6.6382. Min Act: -0.1700
Data Index: 3107380 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4819. Min Range: -7.4819
Max Act: 6.6069. Min Act: -0.1700
Data Index: 1461943 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4819. Min Range: -7.4819
Max Act: 6.6069. Min Act: -0.1700
Data Index: 518103 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4819. Min Range: -7.4819
Max Act: 6.5757. Min Act: -0.1700
Data Index: 6932433 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4819. Min Range: -7.4819
Max Act: 6.5757. Min Act: -0.1700
Data Index: 8405765 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4819. Min Range: -7.4819
Max Act: 6.5757. Min Act: -0.1700
Data Index: 864972 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4819. Min Range: -7.4819
Max Act: 6.5132. Min Act: -0.1700
Data Index: 635513 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4819. Min Range: -7.4819
Max Act: 6.5132. Min Act: -0.1700
Data Index: 8819195 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4819. Min Range: -7.4819
Max Act: 6.5132. Min Act: -0.1700
Data Index: 7387620 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4819. Min Range: -7.4819
Max Act: 6.5132. Min Act: -0.1700
Data Index: 7408009 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4819. Min Range: -7.4819
Max Act: 6.4819. Min Act: -0.1700
Data Index: 5248687 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4819. Min Range: -7.4819
Max Act: 6.4819. Min Act: -0.1700
Data Index: 626493 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19