Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 961 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.5498. Min Act: -0.1700
Data Index: 5279956 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.2833. Min Act: -0.1700
Data Index: 8096494 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.1103. Min Act: -0.1700
Data Index: 1225632 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.1103. Min Act: -0.1700
Data Index: 5466169 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.1103. Min Act: -0.1700
Data Index: 6835945 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.0946. Min Act: -0.1700
Data Index: 5604569 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.0946. Min Act: -0.1700
Data Index: 3555228 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.0788. Min Act: -0.1700
Data Index: 2856587 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.0788. Min Act: -0.1700
Data Index: 725553 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.0472. Min Act: -0.1700
Data Index: 5564674 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.0472. Min Act: -0.1700
Data Index: 1168176 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.0472. Min Act: -0.1700
Data Index: 6529724 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.0630. Min Act: -0.1700
Data Index: 7855409 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.0472. Min Act: -0.1700
Data Index: 3287935 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.0315. Min Act: -0.1700
Data Index: 6577365 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.0315. Min Act: -0.1700
Data Index: 1073949 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.0315. Min Act: -0.1700
Data Index: 1217143 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.0157. Min Act: -0.1700
Data Index: 3834300 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5498. Min Range: -3.5498
Max Act: 3.0157. Min Act: -0.1700
Data Index: 8355748 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5498. Min Range: -3.5498
Max Act: 2.9999. Min Act: -0.1700
Data Index: 6233900 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #19