Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2369 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.5040. Min Act: -0.1700
Data Index: 3905396 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.4415. Min Act: -0.1700
Data Index: 2602386 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.3165. Min Act: -0.1700
Data Index: 5327763 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.2540. Min Act: -0.1700
Data Index: 8111990 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.2228. Min Act: -0.1700
Data Index: 4858493 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.2228. Min Act: -0.1700
Data Index: 1886052 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.1915. Min Act: -0.1700
Data Index: 5366513 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.1603. Min Act: -0.1700
Data Index: 2744320 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.1290. Min Act: -0.1700
Data Index: 2256025 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.1290. Min Act: -0.1700
Data Index: 8702393 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.1603. Min Act: -0.1700
Data Index: 1165094 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.0665. Min Act: -0.1700
Data Index: 4854226 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.0978. Min Act: -0.1700
Data Index: 2830463 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.0665. Min Act: -0.1700
Data Index: 3268599 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.0978. Min Act: -0.1700
Data Index: 8063166 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.0665. Min Act: -0.1700
Data Index: 933568 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.0665. Min Act: -0.1700
Data Index: 1906356 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.0665. Min Act: -0.1700
Data Index: 3919352 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.0353. Min Act: -0.1700
Data Index: 4603391 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5040. Min Range: -5.5040
Max Act: 5.0353. Min Act: -0.1700
Data Index: 110874 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #19