Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2834 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.9236. Min Act: -0.1700
Data Index: 8806384 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.6424. Min Act: -0.1700
Data Index: 157942 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.6111. Min Act: -0.1700
Data Index: 2197441 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.5486. Min Act: -0.1700
Data Index: 2275541 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.5174. Min Act: -0.1700
Data Index: 3837077 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.4861. Min Act: -0.1700
Data Index: 2916174 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.4861. Min Act: -0.1700
Data Index: 539225 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.4549. Min Act: -0.1700
Data Index: 4207783 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.4236. Min Act: -0.1700
Data Index: 8598523 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.4236. Min Act: -0.1700
Data Index: 2019680 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.4236. Min Act: -0.1700
Data Index: 1004323 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.3924. Min Act: -0.1700
Data Index: 6421757 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.3924. Min Act: -0.1700
Data Index: 5301743 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.3611. Min Act: -0.1700
Data Index: 7305359 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.3924. Min Act: -0.1700
Data Index: 7000649 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.3299. Min Act: -0.1700
Data Index: 3136043 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.3299. Min Act: -0.1700
Data Index: 4913307 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.3299. Min Act: -0.1700
Data Index: 3877997 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.2986. Min Act: -0.1700
Data Index: 4684178 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9236. Min Range: -4.9236
Max Act: 4.2986. Min Act: -0.1700
Data Index: 3956107 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19