Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3884 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.6397. Min Act: -0.1700
Data Index: 7691935 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.5771. Min Act: -0.1700
Data Index: 6140326 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.5615. Min Act: -0.1700
Data Index: 8335510 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.5302. Min Act: -0.1700
Data Index: 5875882 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.5458. Min Act: -0.1700
Data Index: 620140 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.5145. Min Act: -0.1700
Data Index: 8453891 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.4832. Min Act: -0.1700
Data Index: 4708996 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.4675. Min Act: -0.1700
Data Index: 3607893 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.4988. Min Act: -0.1700
Data Index: 7444586 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.5302. Min Act: -0.1700
Data Index: 6042925 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.4675. Min Act: -0.1700
Data Index: 3580179 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.4518. Min Act: -0.1700
Data Index: 4978332 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.4518. Min Act: -0.1700
Data Index: 4563125 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.4518. Min Act: -0.1700
Data Index: 3195988 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.4518. Min Act: -0.1700
Data Index: 4755477 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.4362. Min Act: -0.1700
Data Index: 2936881 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.4205. Min Act: -0.1700
Data Index: 5316696 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.4362. Min Act: -0.1700
Data Index: 5268073 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.4048. Min Act: -0.1700
Data Index: 1038035 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6397. Min Range: -3.6397
Max Act: 3.4518. Min Act: -0.1700
Data Index: 3850227 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19