Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2034 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2787. Min Range: -5.2787
Max Act: 5.2787. Min Act: -0.1700
Data Index: 6626566 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2787. Min Range: -5.2787
Max Act: 5.2475. Min Act: -0.1700
Data Index: 5339921 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2787. Min Range: -5.2787
Max Act: 5.2475. Min Act: -0.1700
Data Index: 1967979 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2787. Min Range: -5.2787
Max Act: 5.2162. Min Act: -0.1700
Data Index: 7489065 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2787. Min Range: -5.2787
Max Act: 5.1537. Min Act: -0.1700
Data Index: 8080872 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2787. Min Range: -5.2787
Max Act: 5.0912. Min Act: -0.1700
Data Index: 4621427 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2787. Min Range: -5.2787
Max Act: 5.1225. Min Act: -0.1700
Data Index: 6996873 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2787. Min Range: -5.2787
Max Act: 5.0600. Min Act: -0.1700
Data Index: 7521046 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2787. Min Range: -5.2787
Max Act: 5.0287. Min Act: -0.1700
Data Index: 4352434 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2787. Min Range: -5.2787
Max Act: 5.0287. Min Act: -0.1700
Data Index: 974842 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2787. Min Range: -5.2787
Max Act: 5.0287. Min Act: -0.1700
Data Index: 1517595 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2787. Min Range: -5.2787
Max Act: 4.9975. Min Act: -0.1700
Data Index: 560061 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2787. Min Range: -5.2787
Max Act: 4.9975. Min Act: -0.1700
Data Index: 8494532 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2787. Min Range: -5.2787
Max Act: 4.9662. Min Act: -0.1700
Data Index: 5010256 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2787. Min Range: -5.2787
Max Act: 4.9350. Min Act: -0.1700
Data Index: 2479772 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2787. Min Range: -5.2787
Max Act: 4.9662. Min Act: -0.1700
Data Index: 3338714 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2787. Min Range: -5.2787
Max Act: 4.9350. Min Act: -0.1700
Data Index: 2562011 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2787. Min Range: -5.2787
Max Act: 4.9350. Min Act: -0.1700
Data Index: 2414345 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2787. Min Range: -5.2787
Max Act: 4.9350. Min Act: -0.1700
Data Index: 316574 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2787. Min Range: -5.2787
Max Act: 4.9350. Min Act: -0.1700
Data Index: 1476668 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19