Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1067 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.9762. Min Act: -0.1700
Data Index: 480295 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.6012. Min Act: -0.1700
Data Index: 1261389 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.5699. Min Act: -0.1700
Data Index: 6959149 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.5699. Min Act: -0.1700
Data Index: 3884109 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.5699. Min Act: -0.1700
Data Index: 7014415 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.4449. Min Act: -0.1700
Data Index: 4403236 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.4449. Min Act: -0.1700
Data Index: 4895027 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.3824. Min Act: -0.1700
Data Index: 290650 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.3824. Min Act: -0.1700
Data Index: 7476739 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.2887. Min Act: -0.1700
Data Index: 3048061 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.2887. Min Act: -0.1700
Data Index: 122782 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.2574. Min Act: -0.1700
Data Index: 5504518 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.2887. Min Act: -0.1700
Data Index: 6921331 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.2262. Min Act: -0.1700
Data Index: 3912662 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.2574. Min Act: -0.1700
Data Index: 8649019 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.2574. Min Act: -0.1700
Data Index: 6325427 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.2262. Min Act: -0.1700
Data Index: 2931453 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.2262. Min Act: -0.1700
Data Index: 627371 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.2574. Min Act: -0.1700
Data Index: 6486348 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9762. Min Range: -6.9762
Max Act: 6.1949. Min Act: -0.1700
Data Index: 2762032 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19