Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 569 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.5555. Min Act: -0.1700
Data Index: 148905 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.5394. Min Act: -0.1700
Data Index: 6869909 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4908. Min Act: -0.1700
Data Index: 1158301 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4908. Min Act: -0.1700
Data Index: 5963765 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4746. Min Act: -0.1700
Data Index: 5802186 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4908. Min Act: -0.1700
Data Index: 402036 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4583. Min Act: -0.1700
Data Index: 1975887 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4583. Min Act: -0.1700
Data Index: 1697926 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4421. Min Act: -0.1700
Data Index: 6535280 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4583. Min Act: -0.1700
Data Index: 5379367 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4421. Min Act: -0.1700
Data Index: 8403939 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4421. Min Act: -0.1700
Data Index: 3384423 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4583. Min Act: -0.1700
Data Index: 6264148 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4258. Min Act: -0.1700
Data Index: 4343119 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4258. Min Act: -0.1700
Data Index: 6477343 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4258. Min Act: -0.1700
Data Index: 4610947 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4421. Min Act: -0.1700
Data Index: 5023527 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4421. Min Act: -0.1700
Data Index: 5825183 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4258. Min Act: -0.1700
Data Index: 732794 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5555. Min Range: -2.5555
Max Act: 2.4258. Min Act: -0.1700
Data Index: 8643589 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19