Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4889 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2671. Min Range: -6.2671
Max Act: 6.2671. Min Act: -0.1700
Data Index: 499460 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2671. Min Range: -6.2671
Max Act: 6.2671. Min Act: -0.1700
Data Index: 1908234 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2671. Min Range: -6.2671
Max Act: 6.1109. Min Act: -0.1700
Data Index: 8775725 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2671. Min Range: -6.2671
Max Act: 6.0484. Min Act: -0.1700
Data Index: 6546616 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2671. Min Range: -6.2671
Max Act: 6.0171. Min Act: -0.1700
Data Index: 4655122 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2671. Min Range: -6.2671
Max Act: 6.0171. Min Act: -0.1700
Data Index: 314160 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2671. Min Range: -6.2671
Max Act: 6.0171. Min Act: -0.1700
Data Index: 7363165 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2671. Min Range: -6.2671
Max Act: 5.9859. Min Act: -0.1700
Data Index: 8821069 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2671. Min Range: -6.2671
Max Act: 6.0171. Min Act: -0.1700
Data Index: 6047195 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2671. Min Range: -6.2671
Max Act: 5.9546. Min Act: -0.1700
Data Index: 1040130 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2671. Min Range: -6.2671
Max Act: 5.9234. Min Act: -0.1700
Data Index: 7195215 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2671. Min Range: -6.2671
Max Act: 5.8921. Min Act: -0.1700
Data Index: 5311668 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2671. Min Range: -6.2671
Max Act: 5.8921. Min Act: -0.1700
Data Index: 8385606 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2671. Min Range: -6.2671
Max Act: 5.8609. Min Act: -0.1700
Data Index: 1508610 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2671. Min Range: -6.2671
Max Act: 5.8609. Min Act: -0.1700
Data Index: 3628651 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2671. Min Range: -6.2671
Max Act: 5.8609. Min Act: -0.1700
Data Index: 7946643 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2671. Min Range: -6.2671
Max Act: 5.8609. Min Act: -0.1700
Data Index: 6684178 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2671. Min Range: -6.2671
Max Act: 5.8296. Min Act: -0.1700
Data Index: 6793633 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2671. Min Range: -6.2671
Max Act: 5.8296. Min Act: -0.1700
Data Index: 581728 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2671. Min Range: -6.2671
Max Act: 5.8296. Min Act: -0.1700
Data Index: 8462669 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19