Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3326 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3440. Min Range: -5.3440
Max Act: 5.3440. Min Act: -0.1700
Data Index: 5244439 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3440. Min Range: -5.3440
Max Act: 5.2190. Min Act: -0.1700
Data Index: 5694686 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3440. Min Range: -5.3440
Max Act: 5.1877. Min Act: -0.1700
Data Index: 3064890 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3440. Min Range: -5.3440
Max Act: 5.0627. Min Act: -0.1700
Data Index: 3012982 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3440. Min Range: -5.3440
Max Act: 5.0002. Min Act: -0.1700
Data Index: 5493182 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3440. Min Range: -5.3440
Max Act: 4.9690. Min Act: -0.1700
Data Index: 4442130 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3440. Min Range: -5.3440
Max Act: 4.9690. Min Act: -0.1700
Data Index: 7994782 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3440. Min Range: -5.3440
Max Act: 4.9377. Min Act: -0.1700
Data Index: 409979 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3440. Min Range: -5.3440
Max Act: 4.9377. Min Act: -0.1700
Data Index: 5322673 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3440. Min Range: -5.3440
Max Act: 4.9065. Min Act: -0.1700
Data Index: 7544454 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3440. Min Range: -5.3440
Max Act: 4.9065. Min Act: -0.1700
Data Index: 859541 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3440. Min Range: -5.3440
Max Act: 4.9065. Min Act: -0.1700
Data Index: 2126734 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3440. Min Range: -5.3440
Max Act: 4.9065. Min Act: -0.1700
Data Index: 8448868 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3440. Min Range: -5.3440
Max Act: 4.9065. Min Act: -0.1700
Data Index: 3871 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3440. Min Range: -5.3440
Max Act: 4.9377. Min Act: -0.1700
Data Index: 2272614 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3440. Min Range: -5.3440
Max Act: 4.9065. Min Act: -0.1700
Data Index: 81766 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3440. Min Range: -5.3440
Max Act: 4.8752. Min Act: -0.1700
Data Index: 4060154 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3440. Min Range: -5.3440
Max Act: 4.8752. Min Act: -0.1700
Data Index: 5810069 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3440. Min Range: -5.3440
Max Act: 4.8752. Min Act: -0.1700
Data Index: 7513285 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3440. Min Range: -5.3440
Max Act: 4.8440. Min Act: -0.1700
Data Index: 1470150 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19