Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3811 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.6746. Min Act: -0.1700
Data Index: 6499555 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.6434. Min Act: -0.1700
Data Index: 3540700 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.6434. Min Act: -0.1700
Data Index: 4248207 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.5184. Min Act: -0.1700
Data Index: 2450348 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.4559. Min Act: -0.1700
Data Index: 8257032 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.4871. Min Act: -0.1700
Data Index: 2455748 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.3934. Min Act: -0.1700
Data Index: 5859293 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.3621. Min Act: -0.1700
Data Index: 1580634 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.2996. Min Act: -0.1700
Data Index: 760080 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.3309. Min Act: -0.1700
Data Index: 5893447 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.3309. Min Act: -0.1700
Data Index: 3357504 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.3309. Min Act: -0.1700
Data Index: 3224401 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.2684. Min Act: -0.1700
Data Index: 622102 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.3309. Min Act: -0.1700
Data Index: 3515766 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.2684. Min Act: -0.1700
Data Index: 1902594 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.2684. Min Act: -0.1700
Data Index: 3116154 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.2684. Min Act: -0.1700
Data Index: 3892800 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.2684. Min Act: -0.1700
Data Index: 6148970 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.2684. Min Act: -0.1700
Data Index: 8568761 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6746. Min Range: -5.6746
Max Act: 5.2371. Min Act: -0.1700
Data Index: 6327668 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19