Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6346 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2332. Min Range: -8.2332
Max Act: 8.2332. Min Act: -0.1700
Data Index: 6262166 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2332. Min Range: -8.2332
Max Act: 8.1707. Min Act: -0.1700
Data Index: 7175593 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2332. Min Range: -8.2332
Max Act: 8.1082. Min Act: -0.1700
Data Index: 6683154 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2332. Min Range: -8.2332
Max Act: 8.1082. Min Act: -0.1700
Data Index: 6910913 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2332. Min Range: -8.2332
Max Act: 7.9832. Min Act: -0.1700
Data Index: 7763025 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2332. Min Range: -8.2332
Max Act: 7.9832. Min Act: -0.1700
Data Index: 4167560 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2332. Min Range: -8.2332
Max Act: 7.8582. Min Act: -0.1700
Data Index: 1265166 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2332. Min Range: -8.2332
Max Act: 7.8582. Min Act: -0.1700
Data Index: 6644409 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2332. Min Range: -8.2332
Max Act: 7.8582. Min Act: -0.1700
Data Index: 2735059 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2332. Min Range: -8.2332
Max Act: 7.7957. Min Act: -0.1700
Data Index: 2610096 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2332. Min Range: -8.2332
Max Act: 7.7957. Min Act: -0.1700
Data Index: 6923381 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2332. Min Range: -8.2332
Max Act: 7.7957. Min Act: -0.1700
Data Index: 4022465 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2332. Min Range: -8.2332
Max Act: 7.7957. Min Act: -0.1700
Data Index: 7337526 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2332. Min Range: -8.2332
Max Act: 7.7332. Min Act: -0.1700
Data Index: 3348016 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2332. Min Range: -8.2332
Max Act: 7.7332. Min Act: -0.1700
Data Index: 2506116 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2332. Min Range: -8.2332
Max Act: 7.7332. Min Act: -0.1700
Data Index: 7299353 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2332. Min Range: -8.2332
Max Act: 7.7332. Min Act: -0.1700
Data Index: 3562823 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2332. Min Range: -8.2332
Max Act: 7.7332. Min Act: -0.1700
Data Index: 1462195 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2332. Min Range: -8.2332
Max Act: 7.7332. Min Act: -0.1700
Data Index: 2486101 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2332. Min Range: -8.2332
Max Act: 7.7332. Min Act: -0.1700
Data Index: 3739492 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19