Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5284 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.6355. Min Act: -0.1700
Data Index: 6371901 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.5730. Min Act: -0.1700
Data Index: 5130106 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.5417. Min Act: -0.1700
Data Index: 2335782 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.5105. Min Act: -0.1700
Data Index: 5554003 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.4480. Min Act: -0.1700
Data Index: 5428615 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.4480. Min Act: -0.1700
Data Index: 2458748 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.3230. Min Act: -0.1700
Data Index: 1619960 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.2917. Min Act: -0.1700
Data Index: 3525172 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.2605. Min Act: -0.1700
Data Index: 4380080 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.2605. Min Act: -0.1700
Data Index: 5130126 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.2292. Min Act: -0.1700
Data Index: 5226236 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.1980. Min Act: -0.1700
Data Index: 1652356 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.1667. Min Act: -0.1700
Data Index: 3683165 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.1355. Min Act: -0.1700
Data Index: 6785566 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.1042. Min Act: -0.1700
Data Index: 5130116 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.1042. Min Act: -0.1700
Data Index: 5973006 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.1042. Min Act: -0.1700
Data Index: 88223 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.1042. Min Act: -0.1700
Data Index: 4863795 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.1042. Min Act: -0.1700
Data Index: 1378132 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6355. Min Range: -7.6355
Max Act: 7.0730. Min Act: -0.1700
Data Index: 2801351 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19