Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 478 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.5004. Min Act: -0.1700
Data Index: 4592213 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.4534. Min Act: -0.1700
Data Index: 614547 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.4378. Min Act: -0.1700
Data Index: 7612255 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.4378. Min Act: -0.1700
Data Index: 5437309 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.3751. Min Act: -0.1700
Data Index: 3022110 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.3594. Min Act: -0.1700
Data Index: 3560233 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.3907. Min Act: -0.1700
Data Index: 4247802 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.3907. Min Act: -0.1700
Data Index: 8156132 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.3594. Min Act: -0.1700
Data Index: 263660 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.3437. Min Act: -0.1700
Data Index: 4592209 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.3751. Min Act: -0.1700
Data Index: 7544000 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.3907. Min Act: -0.1700
Data Index: 6765284 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.3594. Min Act: -0.1700
Data Index: 3179849 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.3280. Min Act: -0.1700
Data Index: 7399042 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.3280. Min Act: -0.1700
Data Index: 7948009 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.3123. Min Act: -0.1700
Data Index: 4288751 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.3123. Min Act: -0.1700
Data Index: 6228817 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.3280. Min Act: -0.1700
Data Index: 53999 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.2966. Min Act: -0.1700
Data Index: 1337794 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5004. Min Range: -3.5004
Max Act: 3.2809. Min Act: -0.1700
Data Index: 3620522 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19