Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2403 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.2114. Min Act: -0.1700
Data Index: 7672587 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.1176. Min Act: -0.1700
Data Index: 6952071 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.1176. Min Act: -0.1700
Data Index: 1319124 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.0864. Min Act: -0.1700
Data Index: 7025090 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.0239. Min Act: -0.1700
Data Index: 7025089 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.0239. Min Act: -0.1700
Data Index: 3971912 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2114. Min Range: -5.2114
Max Act: 5.0239. Min Act: -0.1700
Data Index: 3238509 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9614. Min Act: -0.1700
Data Index: 7757538 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9614. Min Act: -0.1700
Data Index: 2386801 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9301. Min Act: -0.1700
Data Index: 4689827 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.9301. Min Act: -0.1700
Data Index: 3337815 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8989. Min Act: -0.1700
Data Index: 6823195 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8989. Min Act: -0.1700
Data Index: 6304891 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8989. Min Act: -0.1700
Data Index: 4171430 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8989. Min Act: -0.1700
Data Index: 4143525 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8989. Min Act: -0.1700
Data Index: 7180168 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8676. Min Act: -0.1700
Data Index: 852333 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8676. Min Act: -0.1700
Data Index: 2038115 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8676. Min Act: -0.1700
Data Index: 5730994 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2114. Min Range: -5.2114
Max Act: 4.8676. Min Act: -0.1700
Data Index: 4938635 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19