Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4596 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3327. Min Range: -10.3327
Max Act: 10.3327. Min Act: -0.1700
Data Index: 3339201 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3327. Min Range: -10.3327
Max Act: 10.2702. Min Act: -0.1700
Data Index: 4861097 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3327. Min Range: -10.3327
Max Act: 10.2077. Min Act: -0.1700
Data Index: 3948133 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.9577. Min Act: -0.1700
Data Index: 3343664 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.8952. Min Act: -0.1700
Data Index: 2632613 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.8952. Min Act: -0.1700
Data Index: 8198002 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.8952. Min Act: -0.1700
Data Index: 1141484 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.8327. Min Act: -0.1700
Data Index: 7134147 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.7702. Min Act: -0.1700
Data Index: 3092591 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.7077. Min Act: -0.1700
Data Index: 7863676 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.7702. Min Act: -0.1700
Data Index: 490676 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.7702. Min Act: -0.1700
Data Index: 1182273 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.7702. Min Act: -0.1700
Data Index: 322830 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.7702. Min Act: -0.1700
Data Index: 1428650 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.6452. Min Act: -0.1700
Data Index: 2978475 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.7077. Min Act: -0.1700
Data Index: 2946210 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.6452. Min Act: -0.1700
Data Index: 4445381 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.6452. Min Act: -0.1700
Data Index: 7342809 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.5827. Min Act: -0.1700
Data Index: 7476754 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3327. Min Range: -10.3327
Max Act: 9.5827. Min Act: -0.1700
Data Index: 7066895 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19