Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4548 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5094. Min Range: -10.5094
Max Act: 10.5094. Min Act: -0.1700
Data Index: 8316479 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5094. Min Range: -10.5094
Max Act: 10.3219. Min Act: -0.1700
Data Index: 5175208 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5094. Min Range: -10.5094
Max Act: 10.2594. Min Act: -0.1700
Data Index: 6527152 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5094. Min Range: -10.5094
Max Act: 10.1969. Min Act: -0.1700
Data Index: 3207642 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5094. Min Range: -10.5094
Max Act: 10.1969. Min Act: -0.1700
Data Index: 4380936 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5094. Min Range: -10.5094
Max Act: 10.0719. Min Act: -0.1700
Data Index: 4122838 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5094. Min Range: -10.5094
Max Act: 10.1344. Min Act: -0.1700
Data Index: 5119350 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5094. Min Range: -10.5094
Max Act: 10.0719. Min Act: -0.1700
Data Index: 4974838 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5094. Min Range: -10.5094
Max Act: 10.0719. Min Act: -0.1700
Data Index: 5510311 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5094. Min Range: -10.5094
Max Act: 10.0719. Min Act: -0.1700
Data Index: 5690246 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5094. Min Range: -10.5094
Max Act: 9.9469. Min Act: -0.1700
Data Index: 1872902 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5094. Min Range: -10.5094
Max Act: 10.0094. Min Act: -0.1700
Data Index: 8797479 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5094. Min Range: -10.5094
Max Act: 9.9469. Min Act: -0.1700
Data Index: 7725241 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5094. Min Range: -10.5094
Max Act: 9.9469. Min Act: -0.1700
Data Index: 79999 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5094. Min Range: -10.5094
Max Act: 9.9469. Min Act: -0.1700
Data Index: 2524079 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5094. Min Range: -10.5094
Max Act: 9.9469. Min Act: -0.1700
Data Index: 3442235 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5094. Min Range: -10.5094
Max Act: 9.8844. Min Act: -0.1700
Data Index: 5020830 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5094. Min Range: -10.5094
Max Act: 9.8844. Min Act: -0.1700
Data Index: 7397497 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5094. Min Range: -10.5094
Max Act: 9.8844. Min Act: -0.1700
Data Index: 4056193 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5094. Min Range: -10.5094
Max Act: 9.8844. Min Act: -0.1700
Data Index: 204884 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19