Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2617 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2567. Min Range: -8.2567
Max Act: 8.2567. Min Act: -0.1700
Data Index: 7437627 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2567. Min Range: -8.2567
Max Act: 8.0692. Min Act: -0.1700
Data Index: 6056362 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2567. Min Range: -8.2567
Max Act: 8.1005. Min Act: -0.1700
Data Index: 5981070 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.8817. Min Act: -0.1700
Data Index: 6548202 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.8817. Min Act: -0.1700
Data Index: 384018 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.8817. Min Act: -0.1700
Data Index: 2968273 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.7880. Min Act: -0.1700
Data Index: 3714636 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.7880. Min Act: -0.1700
Data Index: 279974 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.6942. Min Act: -0.1700
Data Index: 2828320 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.7567. Min Act: -0.1700
Data Index: 5158112 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.6630. Min Act: -0.1700
Data Index: 6536326 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.6317. Min Act: -0.1700
Data Index: 6699103 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.5692. Min Act: -0.1700
Data Index: 3275102 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.6005. Min Act: -0.1700
Data Index: 2102619 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.5692. Min Act: -0.1700
Data Index: 2957414 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.5692. Min Act: -0.1700
Data Index: 7559169 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.5380. Min Act: -0.1700
Data Index: 7516719 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.5380. Min Act: -0.1700
Data Index: 7215795 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.5067. Min Act: -0.1700
Data Index: 6260120 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2567. Min Range: -8.2567
Max Act: 7.5067. Min Act: -0.1700
Data Index: 153884 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19