Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2885 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.5473. Min Act: -0.1700
Data Index: 1008025 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.5159. Min Act: -0.1700
Data Index: 18864 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.5003. Min Act: -0.1700
Data Index: 2915120 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.4689. Min Act: -0.1700
Data Index: 4917050 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.4533. Min Act: -0.1700
Data Index: 451232 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.4376. Min Act: -0.1700
Data Index: 8739149 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.4219. Min Act: -0.1700
Data Index: 5833267 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.4219. Min Act: -0.1700
Data Index: 4558721 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.4219. Min Act: -0.1700
Data Index: 5433428 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.4219. Min Act: -0.1700
Data Index: 2319665 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.4063. Min Act: -0.1700
Data Index: 8471514 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.4063. Min Act: -0.1700
Data Index: 5391598 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.3906. Min Act: -0.1700
Data Index: 677845 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.3906. Min Act: -0.1700
Data Index: 5022856 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.3906. Min Act: -0.1700
Data Index: 643970 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.3906. Min Act: -0.1700
Data Index: 4558720 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.3906. Min Act: -0.1700
Data Index: 5730935 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.3749. Min Act: -0.1700
Data Index: 5538785 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.3749. Min Act: -0.1700
Data Index: 1451490 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5473. Min Range: -3.5473
Max Act: 3.3592. Min Act: -0.1700
Data Index: 507488 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19