Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.3403. Min Act: -0.1700
Data Index: 8453262 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.3403. Min Act: -0.1700
Data Index: 7721084 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.3403. Min Act: -0.1700
Data Index: 5623152 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.2465. Min Act: -0.1700
Data Index: 1611818 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.2153. Min Act: -0.1700
Data Index: 790629 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.2153. Min Act: -0.1700
Data Index: 7665138 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.2153. Min Act: -0.1700
Data Index: 3684377 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.2153. Min Act: -0.1700
Data Index: 524932 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.1840. Min Act: -0.1700
Data Index: 4599291 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.1528. Min Act: -0.1700
Data Index: 1248817 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.1840. Min Act: -0.1700
Data Index: 3073734 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.1215. Min Act: -0.1700
Data Index: 4179369 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.1215. Min Act: -0.1700
Data Index: 2720071 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.0590. Min Act: -0.1700
Data Index: 3490465 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.0590. Min Act: -0.1700
Data Index: 73345 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.0590. Min Act: -0.1700
Data Index: 4310655 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.0278. Min Act: -0.1700
Data Index: 7436533 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.0278. Min Act: -0.1700
Data Index: 5950204 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.0278. Min Act: -0.1700
Data Index: 4394878 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3403. Min Range: -7.3403
Max Act: 7.0278. Min Act: -0.1700
Data Index: 2183205 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19