Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 83 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.7397. Min Act: -0.1700
Data Index: 5371451 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.7397. Min Act: -0.1700
Data Index: 6419765 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.7397. Min Act: -0.1700
Data Index: 2576935 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.7397. Min Act: -0.1700
Data Index: 7954140 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.7084. Min Act: -0.1700
Data Index: 8380082 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.7084. Min Act: -0.1700
Data Index: 2295605 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.7084. Min Act: -0.1700
Data Index: 8806862 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.7397. Min Act: -0.1700
Data Index: 1681194 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.7084. Min Act: -0.1700
Data Index: 1642366 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.6771. Min Act: -0.1700
Data Index: 6177723 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.6771. Min Act: -0.1700
Data Index: 3971202 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.6771. Min Act: -0.1700
Data Index: 3896790 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.6771. Min Act: -0.1700
Data Index: 2032855 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.6458. Min Act: -0.1700
Data Index: 482783 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.6458. Min Act: -0.1700
Data Index: 3279338 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.6458. Min Act: -0.1700
Data Index: 6260804 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.6458. Min Act: -0.1700
Data Index: 4723677 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.6458. Min Act: -0.1700
Data Index: 4795349 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.6145. Min Act: -0.1700
Data Index: 256790 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7397. Min Range: -3.7397
Max Act: 3.6145. Min Act: -0.1700
Data Index: 677293 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19