Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4082 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.7832. Min Act: -0.1700
Data Index: 6055969 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.7520. Min Act: -0.1700
Data Index: 7067206 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.7832. Min Act: -0.1700
Data Index: 7999607 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.7207. Min Act: -0.1700
Data Index: 1406997 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.6895. Min Act: -0.1700
Data Index: 4413445 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.6582. Min Act: -0.1700
Data Index: 4050037 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.6582. Min Act: -0.1700
Data Index: 4773216 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.6582. Min Act: -0.1700
Data Index: 8642195 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.6270. Min Act: -0.1700
Data Index: 659879 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.6270. Min Act: -0.1700
Data Index: 2559431 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.6270. Min Act: -0.1700
Data Index: 6055965 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.6582. Min Act: -0.1700
Data Index: 4413448 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.5645. Min Act: -0.1700
Data Index: 7506308 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.5645. Min Act: -0.1700
Data Index: 885468 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.5957. Min Act: -0.1700
Data Index: 2214767 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.6270. Min Act: -0.1700
Data Index: 627131 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.5957. Min Act: -0.1700
Data Index: 5392632 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.5645. Min Act: -0.1700
Data Index: 5963147 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.5645. Min Act: -0.1700
Data Index: 3903790 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7832. Min Range: -4.7832
Max Act: 4.5645. Min Act: -0.1700
Data Index: 2148716 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19