Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2668 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2304. Min Range: -9.2304
Max Act: 9.2304. Min Act: -0.1700
Data Index: 3068683 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2304. Min Range: -9.2304
Max Act: 9.1679. Min Act: -0.1700
Data Index: 6185755 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2304. Min Range: -9.2304
Max Act: 9.1679. Min Act: -0.1700
Data Index: 455379 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2304. Min Range: -9.2304
Max Act: 9.1054. Min Act: -0.1700
Data Index: 1068774 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2304. Min Range: -9.2304
Max Act: 9.1054. Min Act: -0.1700
Data Index: 8648227 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2304. Min Range: -9.2304
Max Act: 9.1054. Min Act: -0.1700
Data Index: 3171567 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2304. Min Range: -9.2304
Max Act: 9.0429. Min Act: -0.1700
Data Index: 6632191 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2304. Min Range: -9.2304
Max Act: 9.0429. Min Act: -0.1700
Data Index: 1442018 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2304. Min Range: -9.2304
Max Act: 9.0429. Min Act: -0.1700
Data Index: 6182297 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2304. Min Range: -9.2304
Max Act: 9.0429. Min Act: -0.1700
Data Index: 6575644 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2304. Min Range: -9.2304
Max Act: 8.9804. Min Act: -0.1700
Data Index: 4956177 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2304. Min Range: -9.2304
Max Act: 8.9804. Min Act: -0.1700
Data Index: 310460 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2304. Min Range: -9.2304
Max Act: 8.9804. Min Act: -0.1700
Data Index: 2820297 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2304. Min Range: -9.2304
Max Act: 8.9804. Min Act: -0.1700
Data Index: 310482 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2304. Min Range: -9.2304
Max Act: 8.9804. Min Act: -0.1700
Data Index: 4895352 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2304. Min Range: -9.2304
Max Act: 8.9179. Min Act: -0.1700
Data Index: 20167 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2304. Min Range: -9.2304
Max Act: 8.9179. Min Act: -0.1700
Data Index: 5536188 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2304. Min Range: -9.2304
Max Act: 8.9179. Min Act: -0.1700
Data Index: 2004637 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2304. Min Range: -9.2304
Max Act: 8.9179. Min Act: -0.1700
Data Index: 8093984 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2304. Min Range: -9.2304
Max Act: 8.8554. Min Act: -0.1700
Data Index: 4003918 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19