Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4880 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.7743. Min Act: -0.1700
Data Index: 6378223 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.5243. Min Act: -0.1700
Data Index: 2476831 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.4618. Min Act: -0.1700
Data Index: 7695730 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.3993. Min Act: -0.1700
Data Index: 1515647 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.3368. Min Act: -0.1700
Data Index: 3614205 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.2743. Min Act: -0.1700
Data Index: 8259462 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.2118. Min Act: -0.1700
Data Index: 1154952 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.2118. Min Act: -0.1700
Data Index: 2852336 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.2118. Min Act: -0.1700
Data Index: 2655145 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.1493. Min Act: -0.1700
Data Index: 7396473 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.1493. Min Act: -0.1700
Data Index: 4592789 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.1493. Min Act: -0.1700
Data Index: 3263491 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.1493. Min Act: -0.1700
Data Index: 6055480 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.0868. Min Act: -0.1700
Data Index: 4287732 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.1493. Min Act: -0.1700
Data Index: 1359610 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.0868. Min Act: -0.1700
Data Index: 6034829 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.0243. Min Act: -0.1700
Data Index: 2616448 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.0243. Min Act: -0.1700
Data Index: 491196 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.0243. Min Act: -0.1700
Data Index: 2791999 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7743. Min Range: -9.7743
Max Act: 9.0243. Min Act: -0.1700
Data Index: 2942088 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19