Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6128 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1728. Min Range: -8.1728
Max Act: 8.1728. Min Act: -0.1700
Data Index: 1733141 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1728. Min Range: -8.1728
Max Act: 7.7040. Min Act: -0.1700
Data Index: 7637670 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1728. Min Range: -8.1728
Max Act: 7.4228. Min Act: -0.1700
Data Index: 8038405 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1728. Min Range: -8.1728
Max Act: 7.3603. Min Act: -0.1700
Data Index: 8673736 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1728. Min Range: -8.1728
Max Act: 7.3290. Min Act: -0.1700
Data Index: 7231718 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1728. Min Range: -8.1728
Max Act: 7.2978. Min Act: -0.1700
Data Index: 5581083 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1728. Min Range: -8.1728
Max Act: 7.2978. Min Act: -0.1700
Data Index: 7542005 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1728. Min Range: -8.1728
Max Act: 7.2353. Min Act: -0.1700
Data Index: 2858630 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1728. Min Range: -8.1728
Max Act: 7.2040. Min Act: -0.1700
Data Index: 5191058 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1728. Min Range: -8.1728
Max Act: 7.1415. Min Act: -0.1700
Data Index: 6101950 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1728. Min Range: -8.1728
Max Act: 7.1103. Min Act: -0.1700
Data Index: 5872956 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1728. Min Range: -8.1728
Max Act: 7.0478. Min Act: -0.1700
Data Index: 4213112 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1728. Min Range: -8.1728
Max Act: 7.0478. Min Act: -0.1700
Data Index: 6960922 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1728. Min Range: -8.1728
Max Act: 7.0478. Min Act: -0.1700
Data Index: 8516960 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1728. Min Range: -8.1728
Max Act: 7.0478. Min Act: -0.1700
Data Index: 6306668 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1728. Min Range: -8.1728
Max Act: 7.0165. Min Act: -0.1700
Data Index: 4324096 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1728. Min Range: -8.1728
Max Act: 6.9228. Min Act: -0.1700
Data Index: 4636137 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1728. Min Range: -8.1728
Max Act: 6.8915. Min Act: -0.1700
Data Index: 852365 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1728. Min Range: -8.1728
Max Act: 6.8915. Min Act: -0.1700
Data Index: 1003097 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1728. Min Range: -8.1728
Max Act: 6.8603. Min Act: -0.1700
Data Index: 8587882 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19