Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2415 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.3285. Min Act: -0.1700
Data Index: 8302438 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.2972. Min Act: -0.1700
Data Index: 3655771 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.1722. Min Act: -0.1700
Data Index: 3769865 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.1722. Min Act: -0.1700
Data Index: 5819703 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.1097. Min Act: -0.1700
Data Index: 4075301 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.1097. Min Act: -0.1700
Data Index: 3758208 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.0472. Min Act: -0.1700
Data Index: 6923381 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3285. Min Range: -4.3285
Max Act: 4.0159. Min Act: -0.1700
Data Index: 1740792 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3285. Min Range: -4.3285
Max Act: 3.9847. Min Act: -0.1700
Data Index: 1740788 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3285. Min Range: -4.3285
Max Act: 3.9847. Min Act: -0.1700
Data Index: 4368779 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3285. Min Range: -4.3285
Max Act: 3.9847. Min Act: -0.1700
Data Index: 5284904 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3285. Min Range: -4.3285
Max Act: 3.9534. Min Act: -0.1700
Data Index: 6894123 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3285. Min Range: -4.3285
Max Act: 3.9221. Min Act: -0.1700
Data Index: 3166347 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3285. Min Range: -4.3285
Max Act: 3.9534. Min Act: -0.1700
Data Index: 4541834 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3285. Min Range: -4.3285
Max Act: 3.9534. Min Act: -0.1700
Data Index: 6334341 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3285. Min Range: -4.3285
Max Act: 3.9534. Min Act: -0.1700
Data Index: 4573689 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3285. Min Range: -4.3285
Max Act: 3.9534. Min Act: -0.1700
Data Index: 4855126 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3285. Min Range: -4.3285
Max Act: 3.9534. Min Act: -0.1700
Data Index: 7256833 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3285. Min Range: -4.3285
Max Act: 3.9221. Min Act: -0.1700
Data Index: 5015612 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3285. Min Range: -4.3285
Max Act: 3.9534. Min Act: -0.1700
Data Index: 2641835 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19