Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 821 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.4949. Min Act: -0.1700
Data Index: 6160710 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.4949. Min Act: -0.1700
Data Index: 6490810 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.4949. Min Act: -0.1700
Data Index: 2558255 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.4324. Min Act: -0.1700
Data Index: 4710611 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.4324. Min Act: -0.1700
Data Index: 6490809 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.2761. Min Act: -0.1700
Data Index: 3550408 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.2449. Min Act: -0.1700
Data Index: 6591622 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.2761. Min Act: -0.1700
Data Index: 4990456 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.2136. Min Act: -0.1700
Data Index: 3511564 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.2136. Min Act: -0.1700
Data Index: 7803212 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.1824. Min Act: -0.1700
Data Index: 5949075 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.1511. Min Act: -0.1700
Data Index: 3366987 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.1199. Min Act: -0.1700
Data Index: 1247464 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.1199. Min Act: -0.1700
Data Index: 528272 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.0886. Min Act: -0.1700
Data Index: 7290763 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.0574. Min Act: -0.1700
Data Index: 5432998 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.0261. Min Act: -0.1700
Data Index: 6272752 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4949. Min Range: -6.4949
Max Act: 5.9949. Min Act: -0.1700
Data Index: 5084678 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4949. Min Range: -6.4949
Max Act: 6.0261. Min Act: -0.1700
Data Index: 5303678 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4949. Min Range: -6.4949
Max Act: 5.9949. Min Act: -0.1700
Data Index: 7276634 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19