Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1265 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.9105. Min Act: -0.1700
Data Index: 463429 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.8480. Min Act: -0.1700
Data Index: 6678855 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.8792. Min Act: -0.1699
Data Index: 3293457 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.8480. Min Act: -0.1700
Data Index: 7197593 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7855. Min Act: -0.1700
Data Index: 7065654 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.8167. Min Act: -0.1700
Data Index: 1411101 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.8167. Min Act: -0.1700
Data Index: 6543335 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.8167. Min Act: -0.1700
Data Index: 4710375 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7855. Min Act: -0.1700
Data Index: 6111203 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7855. Min Act: -0.1700
Data Index: 4019191 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7542. Min Act: -0.1700
Data Index: 1528419 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7542. Min Act: -0.1700
Data Index: 1000414 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7542. Min Act: -0.1700
Data Index: 7780897 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7542. Min Act: -0.1700
Data Index: 4805601 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7542. Min Act: -0.1700
Data Index: 3223713 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7230. Min Act: -0.1700
Data Index: 3458191 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7230. Min Act: -0.1700
Data Index: 911178 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.6917. Min Act: -0.1700
Data Index: 1632374 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7230. Min Act: -0.1700
Data Index: 6097795 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9105. Min Range: -5.9105
Max Act: 5.7230. Min Act: -0.1700
Data Index: 4503788 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19