Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3828 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.8791. Min Act: -0.1700
Data Index: 3780230 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.8166. Min Act: -0.1700
Data Index: 8417031 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.7541. Min Act: -0.1700
Data Index: 3804121 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.7541. Min Act: -0.1700
Data Index: 3938940 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.6291. Min Act: -0.1700
Data Index: 3293198 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.6916. Min Act: -0.1700
Data Index: 190666 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.6916. Min Act: -0.1700
Data Index: 3864170 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.5666. Min Act: -0.1700
Data Index: 5939173 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.5041. Min Act: -0.1700
Data Index: 3419589 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.5041. Min Act: -0.1700
Data Index: 3722388 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.3166. Min Act: -0.1700
Data Index: 5485560 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.3166. Min Act: -0.1700
Data Index: 3811701 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.2541. Min Act: -0.1700
Data Index: 6442747 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1916. Min Act: -0.1700
Data Index: 7997747 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1916. Min Act: -0.1700
Data Index: 8451573 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1916. Min Act: -0.1700
Data Index: 8014101 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1916. Min Act: -0.1700
Data Index: 3244142 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1916. Min Act: -0.1699
Data Index: 6737140 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1916. Min Act: -0.1700
Data Index: 2896799 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8791. Min Range: -8.8791
Max Act: 8.1291. Min Act: -0.1700
Data Index: 5007544 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19