Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2833 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8473. Min Range: -10.8473
Max Act: 10.8473. Min Act: -0.1700
Data Index: 2461697 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8473. Min Range: -10.8473
Max Act: 10.5973. Min Act: -0.1700
Data Index: 1157030 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8473. Min Range: -10.8473
Max Act: 10.5348. Min Act: -0.1700
Data Index: 5931242 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8473. Min Range: -10.8473
Max Act: 10.0348. Min Act: -0.1700
Data Index: 1794075 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8473. Min Range: -10.8473
Max Act: 9.9723. Min Act: -0.1700
Data Index: 7028851 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8473. Min Range: -10.8473
Max Act: 9.9723. Min Act: -0.1700
Data Index: 6250449 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8473. Min Range: -10.8473
Max Act: 9.9098. Min Act: -0.1700
Data Index: 1517342 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8473. Min Range: -10.8473
Max Act: 9.9098. Min Act: -0.1700
Data Index: 1290083 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8473. Min Range: -10.8473
Max Act: 9.9098. Min Act: -0.1700
Data Index: 7571493 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8473. Min Range: -10.8473
Max Act: 9.9098. Min Act: -0.1700
Data Index: 6651225 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8473. Min Range: -10.8473
Max Act: 9.9098. Min Act: -0.1700
Data Index: 3714961 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8473. Min Range: -10.8473
Max Act: 9.8473. Min Act: -0.1700
Data Index: 8206183 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8473. Min Range: -10.8473
Max Act: 9.9098. Min Act: -0.1700
Data Index: 6915929 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8473. Min Range: -10.8473
Max Act: 9.9098. Min Act: -0.1700
Data Index: 7866457 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8473. Min Range: -10.8473
Max Act: 9.7848. Min Act: -0.1700
Data Index: 136329 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8473. Min Range: -10.8473
Max Act: 9.7848. Min Act: -0.1700
Data Index: 6168740 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8473. Min Range: -10.8473
Max Act: 9.7848. Min Act: -0.1700
Data Index: 7673838 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8473. Min Range: -10.8473
Max Act: 9.7223. Min Act: -0.1700
Data Index: 5956081 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8473. Min Range: -10.8473
Max Act: 9.7223. Min Act: -0.1700
Data Index: 6696110 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8473. Min Range: -10.8473
Max Act: 9.6598. Min Act: -0.1700
Data Index: 4179521 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19