Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1971 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.4253. Min Act: -0.1700
Data Index: 4506980 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.4566. Min Act: -0.1700
Data Index: 8399464 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.3316. Min Act: -0.1700
Data Index: 1821037 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.2691. Min Act: -0.1700
Data Index: 1145268 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.2691. Min Act: -0.1700
Data Index: 6071939 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.2066. Min Act: -0.1700
Data Index: 81230 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.2066. Min Act: -0.1700
Data Index: 4296276 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.2066. Min Act: -0.1700
Data Index: 3493856 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.1753. Min Act: -0.1700
Data Index: 7331607 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.1441. Min Act: -0.1700
Data Index: 943731 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.1441. Min Act: -0.1700
Data Index: 5745787 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.1441. Min Act: -0.1700
Data Index: 1179254 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.1441. Min Act: -0.1700
Data Index: 3039088 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.0816. Min Act: -0.1700
Data Index: 4935270 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.0503. Min Act: -0.1700
Data Index: 6858542 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.0503. Min Act: -0.1700
Data Index: 154659 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.0503. Min Act: -0.1700
Data Index: 5962956 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.0503. Min Act: -0.1700
Data Index: 6835460 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.0191. Min Act: -0.1700
Data Index: 7019479 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4566. Min Range: -7.4566
Max Act: 7.0191. Min Act: -0.1700
Data Index: 7553672 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19