Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5439 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3226. Min Range: -7.3226
Max Act: 7.3226. Min Act: -0.1700
Data Index: 5936229 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.9476. Min Act: -0.1700
Data Index: 4824479 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.7288. Min Act: -0.1700
Data Index: 4415666 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.6663. Min Act: -0.1700
Data Index: 5865874 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.5726. Min Act: -0.1700
Data Index: 5776852 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.5101. Min Act: -0.1700
Data Index: 3444655 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.5101. Min Act: -0.1700
Data Index: 3684435 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.4476. Min Act: -0.1700
Data Index: 5343484 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.3538. Min Act: -0.1700
Data Index: 5967420 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.3538. Min Act: -0.1700
Data Index: 4522605 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.3538. Min Act: -0.1700
Data Index: 6401768 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.3538. Min Act: -0.1700
Data Index: 7446209 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.3226. Min Act: -0.1700
Data Index: 4683226 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.3226. Min Act: -0.1700
Data Index: 5651753 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.3226. Min Act: -0.1700
Data Index: 4401054 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.2913. Min Act: -0.1700
Data Index: 7377453 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.2913. Min Act: -0.1700
Data Index: 3996873 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.2913. Min Act: -0.1700
Data Index: 341987 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.2601. Min Act: -0.1700
Data Index: 410676 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3226. Min Range: -7.3226
Max Act: 6.2601. Min Act: -0.1700
Data Index: 401947 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19