Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3795 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.4605. Min Act: -0.1700
Data Index: 4397304 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.3508. Min Act: -0.1700
Data Index: 8543754 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.1937. Min Act: -0.1700
Data Index: 3782617 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.1623. Min Act: -0.1700
Data Index: 5281375 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.1623. Min Act: -0.1700
Data Index: 1885890 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.1308. Min Act: -0.1700
Data Index: 533169 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.1150. Min Act: -0.1700
Data Index: 6839522 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.1150. Min Act: -0.1700
Data Index: 640467 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.1150. Min Act: -0.1700
Data Index: 3239606 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.0993. Min Act: -0.1700
Data Index: 7755691 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.0993. Min Act: -0.1700
Data Index: 5717847 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.0835. Min Act: -0.1700
Data Index: 8208056 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.0835. Min Act: -0.1700
Data Index: 4542608 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.0677. Min Act: -0.1700
Data Index: 7246607 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.0677. Min Act: -0.1700
Data Index: 894023 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.0520. Min Act: -0.1700
Data Index: 4187160 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.0520. Min Act: -0.1700
Data Index: 6497349 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.0520. Min Act: -0.1700
Data Index: 7272058 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.0677. Min Act: -0.1700
Data Index: 2929163 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4605. Min Range: -3.4605
Max Act: 3.0520. Min Act: -0.1700
Data Index: 5530058 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19