Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3311 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.8398. Min Act: -0.1700
Data Index: 5586848 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.7460. Min Act: -0.1700
Data Index: 8513440 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.7460. Min Act: -0.1700
Data Index: 3814678 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.7148. Min Act: -0.1700
Data Index: 7532446 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.7148. Min Act: -0.1700
Data Index: 6322533 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.6835. Min Act: -0.1700
Data Index: 8070336 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.6835. Min Act: -0.1700
Data Index: 1170096 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.6210. Min Act: -0.1700
Data Index: 4662368 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.5585. Min Act: -0.1700
Data Index: 6372101 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.5273. Min Act: -0.1700
Data Index: 6431316 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.5273. Min Act: -0.1700
Data Index: 7422765 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.4648. Min Act: -0.1700
Data Index: 4146933 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.4023. Min Act: -0.1700
Data Index: 6978235 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.3710. Min Act: -0.1700
Data Index: 3285138 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.3398. Min Act: -0.1700
Data Index: 7699662 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.3710. Min Act: -0.1700
Data Index: 1672874 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.3398. Min Act: -0.1700
Data Index: 6134112 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.3398. Min Act: -0.1700
Data Index: 6439767 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.3085. Min Act: -0.1700
Data Index: 261263 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8398. Min Range: -5.8398
Max Act: 5.2773. Min Act: -0.1700
Data Index: 5828868 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19