Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2877 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4320. Min Range: -6.4320
Max Act: 6.4320. Min Act: -0.1700
Data Index: 6397112 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4320. Min Range: -6.4320
Max Act: 6.4007. Min Act: -0.1700
Data Index: 2690649 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4320. Min Range: -6.4320
Max Act: 6.2757. Min Act: -0.1700
Data Index: 4620348 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4320. Min Range: -6.4320
Max Act: 6.2445. Min Act: -0.1700
Data Index: 5094866 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4320. Min Range: -6.4320
Max Act: 6.2132. Min Act: -0.1700
Data Index: 4291297 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4320. Min Range: -6.4320
Max Act: 6.1820. Min Act: -0.1700
Data Index: 3622352 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4320. Min Range: -6.4320
Max Act: 6.1507. Min Act: -0.1700
Data Index: 3462056 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4320. Min Range: -6.4320
Max Act: 6.1195. Min Act: -0.1700
Data Index: 5473129 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4320. Min Range: -6.4320
Max Act: 6.1195. Min Act: -0.1700
Data Index: 4041234 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4320. Min Range: -6.4320
Max Act: 6.0882. Min Act: -0.1700
Data Index: 2375115 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4320. Min Range: -6.4320
Max Act: 6.0882. Min Act: -0.1700
Data Index: 4416748 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4320. Min Range: -6.4320
Max Act: 6.0257. Min Act: -0.1700
Data Index: 3537606 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4320. Min Range: -6.4320
Max Act: 6.0257. Min Act: -0.1700
Data Index: 65730 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4320. Min Range: -6.4320
Max Act: 6.0257. Min Act: -0.1700
Data Index: 1147071 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4320. Min Range: -6.4320
Max Act: 6.0257. Min Act: -0.1700
Data Index: 3591035 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4320. Min Range: -6.4320
Max Act: 5.9945. Min Act: -0.1700
Data Index: 4845440 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4320. Min Range: -6.4320
Max Act: 5.9945. Min Act: -0.1700
Data Index: 7520217 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4320. Min Range: -6.4320
Max Act: 5.9632. Min Act: -0.1700
Data Index: 4837143 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4320. Min Range: -6.4320
Max Act: 5.9632. Min Act: -0.1700
Data Index: 552031 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4320. Min Range: -6.4320
Max Act: 5.9320. Min Act: -0.1700
Data Index: 5988148 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #19