Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5065 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1735. Min Range: -2.1735
Max Act: 2.1735. Min Act: -0.1700
Data Index: 6448026 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1735. Min Range: -2.1735
Max Act: 2.1402. Min Act: -0.1700
Data Index: 2170775 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1735. Min Range: -2.1735
Max Act: 2.1068. Min Act: -0.1700
Data Index: 4913429 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1735. Min Range: -2.1735
Max Act: 2.0397. Min Act: -0.1700
Data Index: 4216889 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1735. Min Range: -2.1735
Max Act: 2.0059. Min Act: -0.1700
Data Index: 1112405 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1735. Min Range: -2.1735
Max Act: 2.0228. Min Act: -0.1700
Data Index: 2436223 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1735. Min Range: -2.1735
Max Act: 2.0228. Min Act: -0.1699
Data Index: 1568520 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1735. Min Range: -2.1735
Max Act: 1.9721. Min Act: -0.1700
Data Index: 3035290 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1735. Min Range: -2.1735
Max Act: 1.9721. Min Act: -0.1700
Data Index: 158963 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1735. Min Range: -2.1735
Max Act: 1.9890. Min Act: -0.1700
Data Index: 906008 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1735. Min Range: -2.1735
Max Act: 1.9211. Min Act: -0.1700
Data Index: 1198804 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1735. Min Range: -2.1735
Max Act: 1.9551. Min Act: -0.1700
Data Index: 556719 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1735. Min Range: -2.1735
Max Act: 1.9382. Min Act: -0.1700
Data Index: 3239343 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1735. Min Range: -2.1735
Max Act: 1.9551. Min Act: -0.1700
Data Index: 4216885 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1735. Min Range: -2.1735
Max Act: 1.9551. Min Act: -0.1700
Data Index: 4690961 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1735. Min Range: -2.1735
Max Act: 1.9721. Min Act: -0.1700
Data Index: 6565199 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1735. Min Range: -2.1735
Max Act: 1.9382. Min Act: -0.1700
Data Index: 1188318 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1735. Min Range: -2.1735
Max Act: 1.9551. Min Act: -0.1700
Data Index: 446726 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1735. Min Range: -2.1735
Max Act: 1.9551. Min Act: -0.1700
Data Index: 4216884 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1735. Min Range: -2.1735
Max Act: 1.9041. Min Act: -0.1700
Data Index: 3668758 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19