Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3927 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.9625. Min Act: -0.1700
Data Index: 4568205 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.8687. Min Act: -0.1700
Data Index: 4929156 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.8375. Min Act: -0.1700
Data Index: 5907877 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.8062. Min Act: -0.1700
Data Index: 867382 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.8062. Min Act: -0.1700
Data Index: 2236480 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.8062. Min Act: -0.1700
Data Index: 1393861 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.8062. Min Act: -0.1700
Data Index: 6224557 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.7437. Min Act: -0.1700
Data Index: 6951236 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.7437. Min Act: -0.1700
Data Index: 5416184 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.7125. Min Act: -0.1700
Data Index: 7084996 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.7125. Min Act: -0.1700
Data Index: 2532942 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6812. Min Act: -0.1700
Data Index: 8732015 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6812. Min Act: -0.1700
Data Index: 3980938 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6500. Min Act: -0.1700
Data Index: 2176156 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6500. Min Act: -0.1700
Data Index: 1970093 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6500. Min Act: -0.1700
Data Index: 6013414 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6187. Min Act: -0.1700
Data Index: 1544707 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6187. Min Act: -0.1700
Data Index: 3918719 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6187. Min Act: -0.1700
Data Index: 4999985 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9625. Min Range: -6.9625
Max Act: 6.6187. Min Act: -0.1700
Data Index: 5992848 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19