Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3601 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2584. Min Range: -7.2584
Max Act: 7.2584. Min Act: -0.1700
Data Index: 4542757 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2584. Min Range: -7.2584
Max Act: 7.2584. Min Act: -0.1700
Data Index: 8293244 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2584. Min Range: -7.2584
Max Act: 7.1334. Min Act: -0.1700
Data Index: 2802672 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2584. Min Range: -7.2584
Max Act: 7.1334. Min Act: -0.1700
Data Index: 5692361 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2584. Min Range: -7.2584
Max Act: 7.1334. Min Act: -0.1700
Data Index: 1909068 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2584. Min Range: -7.2584
Max Act: 7.1334. Min Act: -0.1700
Data Index: 2736570 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2584. Min Range: -7.2584
Max Act: 7.1334. Min Act: -0.1700
Data Index: 5779491 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2584. Min Range: -7.2584
Max Act: 7.0709. Min Act: -0.1700
Data Index: 8749039 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2584. Min Range: -7.2584
Max Act: 7.0709. Min Act: -0.1700
Data Index: 2736571 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2584. Min Range: -7.2584
Max Act: 7.0709. Min Act: -0.1700
Data Index: 7463848 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2584. Min Range: -7.2584
Max Act: 7.0084. Min Act: -0.1699
Data Index: 3026275 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2584. Min Range: -7.2584
Max Act: 7.0084. Min Act: -0.1700
Data Index: 1369616 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2584. Min Range: -7.2584
Max Act: 6.9772. Min Act: -0.1700
Data Index: 984691 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2584. Min Range: -7.2584
Max Act: 6.9772. Min Act: -0.1700
Data Index: 3257244 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2584. Min Range: -7.2584
Max Act: 6.9772. Min Act: -0.1700
Data Index: 6706420 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2584. Min Range: -7.2584
Max Act: 6.9772. Min Act: -0.1700
Data Index: 8031572 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2584. Min Range: -7.2584
Max Act: 6.9459. Min Act: -0.1700
Data Index: 2349005 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2584. Min Range: -7.2584
Max Act: 6.9459. Min Act: -0.1700
Data Index: 5968984 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2584. Min Range: -7.2584
Max Act: 6.8834. Min Act: -0.1700
Data Index: 984697 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2584. Min Range: -7.2584
Max Act: 6.9147. Min Act: -0.1700
Data Index: 5373800 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19