Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2735 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2563. Min Range: -10.2563
Max Act: 10.2563. Min Act: -0.1700
Data Index: 5268197 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2563. Min Range: -10.2563
Max Act: 10.0688. Min Act: -0.1700
Data Index: 5824384 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.9438. Min Act: -0.1700
Data Index: 2080659 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2563. Min Range: -10.2563
Max Act: 10.0063. Min Act: -0.1700
Data Index: 4520087 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.9438. Min Act: -0.1700
Data Index: 6380769 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.9438. Min Act: -0.1700
Data Index: 7346176 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.9438. Min Act: -0.1700
Data Index: 7916143 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.8813. Min Act: -0.1700
Data Index: 5813698 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.8813. Min Act: -0.1700
Data Index: 337975 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.8813. Min Act: -0.1700
Data Index: 4754179 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.8813. Min Act: -0.1700
Data Index: 3571878 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.7563. Min Act: -0.1700
Data Index: 4186970 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.6938. Min Act: -0.1700
Data Index: 213725 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.7563. Min Act: -0.1700
Data Index: 4858105 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.7563. Min Act: -0.1700
Data Index: 820141 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.6938. Min Act: -0.1700
Data Index: 3943811 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.6938. Min Act: -0.1700
Data Index: 2251446 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.6313. Min Act: -0.1700
Data Index: 7708418 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.6313. Min Act: -0.1700
Data Index: 5402666 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2563. Min Range: -10.2563
Max Act: 9.6313. Min Act: -0.1700
Data Index: 5984505 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19