Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4814 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1632. Min Range: -7.1632
Max Act: 7.1632. Min Act: -0.1700
Data Index: 1130027 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1632. Min Range: -7.1632
Max Act: 7.1007. Min Act: -0.1700
Data Index: 466094 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.4757. Min Act: -0.1700
Data Index: 4017583 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.4444. Min Act: -0.1700
Data Index: 3825547 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.3194. Min Act: -0.1700
Data Index: 1027499 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.3194. Min Act: -0.1700
Data Index: 3572511 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.2882. Min Act: -0.1700
Data Index: 6787952 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.2569. Min Act: -0.1700
Data Index: 3029758 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.2257. Min Act: -0.1700
Data Index: 6981826 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.2569. Min Act: -0.1700
Data Index: 8274924 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.2257. Min Act: -0.1700
Data Index: 34496 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.1944. Min Act: -0.1700
Data Index: 7726255 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.1944. Min Act: -0.1700
Data Index: 4594226 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.1632. Min Act: -0.1700
Data Index: 8557813 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.1632. Min Act: -0.1700
Data Index: 676834 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.1632. Min Act: -0.1700
Data Index: 7369282 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.1319. Min Act: -0.1700
Data Index: 2493164 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.1319. Min Act: -0.1700
Data Index: 8762326 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.0694. Min Act: -0.1700
Data Index: 5646609 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1632. Min Range: -7.1632
Max Act: 6.1007. Min Act: -0.1700
Data Index: 288872 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19