Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1888 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2964. Min Range: -7.2964
Max Act: 7.2964. Min Act: -0.1700
Data Index: 79429 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2964. Min Range: -7.2964
Max Act: 7.1401. Min Act: -0.1700
Data Index: 2177466 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2964. Min Range: -7.2964
Max Act: 7.1089. Min Act: -0.1700
Data Index: 3929953 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2964. Min Range: -7.2964
Max Act: 7.0776. Min Act: -0.1700
Data Index: 4212508 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2964. Min Range: -7.2964
Max Act: 7.0776. Min Act: -0.1700
Data Index: 3540776 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2964. Min Range: -7.2964
Max Act: 7.0151. Min Act: -0.1700
Data Index: 2422847 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2964. Min Range: -7.2964
Max Act: 7.0464. Min Act: -0.1700
Data Index: 5181991 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2964. Min Range: -7.2964
Max Act: 7.0151. Min Act: -0.1700
Data Index: 3102107 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2964. Min Range: -7.2964
Max Act: 6.9526. Min Act: -0.1700
Data Index: 5592427 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2964. Min Range: -7.2964
Max Act: 6.9214. Min Act: -0.1700
Data Index: 497773 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2964. Min Range: -7.2964
Max Act: 6.8901. Min Act: -0.1700
Data Index: 5851530 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2964. Min Range: -7.2964
Max Act: 6.8901. Min Act: -0.1700
Data Index: 2246000 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2964. Min Range: -7.2964
Max Act: 6.8589. Min Act: -0.1700
Data Index: 7780132 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2964. Min Range: -7.2964
Max Act: 6.8901. Min Act: -0.1700
Data Index: 6381316 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2964. Min Range: -7.2964
Max Act: 6.8589. Min Act: -0.1700
Data Index: 6358527 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2964. Min Range: -7.2964
Max Act: 6.8589. Min Act: -0.1700
Data Index: 256140 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2964. Min Range: -7.2964
Max Act: 6.8276. Min Act: -0.1700
Data Index: 1791027 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2964. Min Range: -7.2964
Max Act: 6.8276. Min Act: -0.1700
Data Index: 7008758 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2964. Min Range: -7.2964
Max Act: 6.7964. Min Act: -0.1700
Data Index: 675172 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2964. Min Range: -7.2964
Max Act: 6.7964. Min Act: -0.1700
Data Index: 2863339 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19