Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 704 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3077. Min Range: -6.3077
Max Act: 6.3077. Min Act: -0.1700
Data Index: 4469029 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3077. Min Range: -6.3077
Max Act: 6.0890. Min Act: -0.1700
Data Index: 7526844 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.9327. Min Act: -0.1700
Data Index: 2695909 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.8702. Min Act: -0.1700
Data Index: 5672791 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.7765. Min Act: -0.1700
Data Index: 3867035 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.7765. Min Act: -0.1700
Data Index: 636665 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.7452. Min Act: -0.1700
Data Index: 2988784 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.7452. Min Act: -0.1700
Data Index: 414935 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.6515. Min Act: -0.1700
Data Index: 5633178 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.6202. Min Act: -0.1700
Data Index: 5417902 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.5890. Min Act: -0.1700
Data Index: 2867423 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.5577. Min Act: -0.1700
Data Index: 3318659 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.5265. Min Act: -0.1700
Data Index: 7685578 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.5265. Min Act: -0.1700
Data Index: 1749535 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.5265. Min Act: -0.1700
Data Index: 6133008 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.5265. Min Act: -0.1700
Data Index: 488445 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.5265. Min Act: -0.1700
Data Index: 2326159 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.5265. Min Act: -0.1700
Data Index: 5087014 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.5265. Min Act: -0.1700
Data Index: 1054858 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3077. Min Range: -6.3077
Max Act: 5.4952. Min Act: -0.1700
Data Index: 3233393 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19