Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3481 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.9222. Min Act: -0.1700
Data Index: 647054 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.8910. Min Act: -0.1700
Data Index: 6794747 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.8284. Min Act: -0.1700
Data Index: 5237541 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.7972. Min Act: -0.1700
Data Index: 7859335 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.8284. Min Act: -0.1700
Data Index: 3727801 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.7972. Min Act: -0.1700
Data Index: 6950572 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.7346. Min Act: -0.1700
Data Index: 5613258 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.7346. Min Act: -0.1700
Data Index: 4812467 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.7190. Min Act: -0.1700
Data Index: 6531990 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.7190. Min Act: -0.1700
Data Index: 414176 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.7033. Min Act: -0.1700
Data Index: 7423516 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.6877. Min Act: -0.1700
Data Index: 5160319 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.6877. Min Act: -0.1700
Data Index: 4423733 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.6877. Min Act: -0.1700
Data Index: 5255532 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.7190. Min Act: -0.1700
Data Index: 8577117 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.6564. Min Act: -0.1700
Data Index: 5665164 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.6564. Min Act: -0.1700
Data Index: 1261215 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.6564. Min Act: -0.1700
Data Index: 3978471 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.6720. Min Act: -0.1700
Data Index: 4464488 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9222. Min Range: -3.9222
Max Act: 3.6564. Min Act: -0.1700
Data Index: 2157098 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19