Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6040 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.4166. Min Act: -0.1700
Data Index: 4391982 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.4478. Min Act: -0.1700
Data Index: 3576246 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.3853. Min Act: -0.1700
Data Index: 858470 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.3541. Min Act: -0.1700
Data Index: 1805529 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.3541. Min Act: -0.1700
Data Index: 1910356 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.3541. Min Act: -0.1700
Data Index: 8486804 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.3228. Min Act: -0.1700
Data Index: 4629055 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.2603. Min Act: -0.1700
Data Index: 4044711 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.2603. Min Act: -0.1700
Data Index: 1353964 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.2291. Min Act: -0.1700
Data Index: 1736519 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.2291. Min Act: -0.1700
Data Index: 4627952 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.2291. Min Act: -0.1700
Data Index: 2046568 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.1978. Min Act: -0.1700
Data Index: 2906559 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.1978. Min Act: -0.1700
Data Index: 8575594 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.1666. Min Act: -0.1700
Data Index: 3933562 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.1666. Min Act: -0.1700
Data Index: 5898473 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.1353. Min Act: -0.1700
Data Index: 146529 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.1353. Min Act: -0.1700
Data Index: 1607532 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.1353. Min Act: -0.1700
Data Index: 3410363 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4478. Min Range: -5.4478
Max Act: 5.1353. Min Act: -0.1700
Data Index: 1332633 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19