Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 196 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0207. Min Range: -9.0207
Max Act: 9.0207. Min Act: -0.1700
Data Index: 2067145 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.9582. Min Act: -0.1700
Data Index: 8655525 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.8332. Min Act: -0.1700
Data Index: 3022692 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.7082. Min Act: -0.1700
Data Index: 18196 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.6457. Min Act: -0.1700
Data Index: 2209761 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.5832. Min Act: -0.1700
Data Index: 863734 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.5832. Min Act: -0.1700
Data Index: 814934 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.5832. Min Act: -0.1700
Data Index: 292391 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.5207. Min Act: -0.1700
Data Index: 1275098 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.5207. Min Act: -0.1700
Data Index: 4780737 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.4582. Min Act: -0.1700
Data Index: 5829087 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.4582. Min Act: -0.1700
Data Index: 6907889 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.5207. Min Act: -0.1700
Data Index: 4704450 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.3957. Min Act: -0.1700
Data Index: 492372 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.4582. Min Act: -0.1700
Data Index: 6684237 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.4582. Min Act: -0.1700
Data Index: 2014299 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.3957. Min Act: -0.1700
Data Index: 3486222 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.3957. Min Act: -0.1700
Data Index: 4383960 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.3957. Min Act: -0.1700
Data Index: 6757970 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0207. Min Range: -9.0207
Max Act: 8.3957. Min Act: -0.1700
Data Index: 4678083 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19