Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5098 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1722. Min Range: -7.1722
Max Act: 7.1722. Min Act: -0.1700
Data Index: 2818926 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1722. Min Range: -7.1722
Max Act: 7.0472. Min Act: -0.1700
Data Index: 4215097 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1722. Min Range: -7.1722
Max Act: 7.0160. Min Act: -0.1700
Data Index: 2818930 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.9222. Min Act: -0.1700
Data Index: 6330089 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.9222. Min Act: -0.1700
Data Index: 3278119 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.8910. Min Act: -0.1700
Data Index: 8235521 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.8597. Min Act: -0.1700
Data Index: 2818927 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.8910. Min Act: -0.1700
Data Index: 2818929 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.8597. Min Act: -0.1700
Data Index: 2808917 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.8285. Min Act: -0.1700
Data Index: 3550324 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.8597. Min Act: -0.1700
Data Index: 277090 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.8285. Min Act: -0.1700
Data Index: 4666136 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.7972. Min Act: -0.1700
Data Index: 8235519 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.7660. Min Act: -0.1700
Data Index: 1101287 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.7660. Min Act: -0.1700
Data Index: 1657979 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.7035. Min Act: -0.1700
Data Index: 3234319 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.6722. Min Act: -0.1700
Data Index: 2508469 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.6410. Min Act: -0.1700
Data Index: 1061035 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.6097. Min Act: -0.1700
Data Index: 157586 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1722. Min Range: -7.1722
Max Act: 6.5472. Min Act: -0.1700
Data Index: 5996942 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19