Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4354 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2707. Min Range: -5.2707
Max Act: 5.2707. Min Act: -0.1700
Data Index: 5855019 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2707. Min Range: -5.2707
Max Act: 5.2394. Min Act: -0.1700
Data Index: 4825919 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2707. Min Range: -5.2707
Max Act: 5.1144. Min Act: -0.1700
Data Index: 941352 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2707. Min Range: -5.2707
Max Act: 5.1144. Min Act: -0.1700
Data Index: 6298236 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2707. Min Range: -5.2707
Max Act: 5.1144. Min Act: -0.1700
Data Index: 2594837 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2707. Min Range: -5.2707
Max Act: 5.0519. Min Act: -0.1700
Data Index: 1425897 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2707. Min Range: -5.2707
Max Act: 4.9582. Min Act: -0.1700
Data Index: 3534083 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2707. Min Range: -5.2707
Max Act: 4.9582. Min Act: -0.1700
Data Index: 231907 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2707. Min Range: -5.2707
Max Act: 4.9582. Min Act: -0.1700
Data Index: 678907 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2707. Min Range: -5.2707
Max Act: 4.9582. Min Act: -0.1700
Data Index: 7049949 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2707. Min Range: -5.2707
Max Act: 4.9582. Min Act: -0.1700
Data Index: 8207567 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2707. Min Range: -5.2707
Max Act: 4.8957. Min Act: -0.1700
Data Index: 4600978 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2707. Min Range: -5.2707
Max Act: 4.9269. Min Act: -0.1700
Data Index: 5660695 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2707. Min Range: -5.2707
Max Act: 4.9269. Min Act: -0.1700
Data Index: 646875 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2707. Min Range: -5.2707
Max Act: 4.9269. Min Act: -0.1700
Data Index: 3781421 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2707. Min Range: -5.2707
Max Act: 4.9269. Min Act: -0.1700
Data Index: 8053024 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2707. Min Range: -5.2707
Max Act: 4.9582. Min Act: -0.1700
Data Index: 13413 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2707. Min Range: -5.2707
Max Act: 4.8957. Min Act: -0.1700
Data Index: 5711306 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2707. Min Range: -5.2707
Max Act: 4.9269. Min Act: -0.1700
Data Index: 8379411 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2707. Min Range: -5.2707
Max Act: 4.8644. Min Act: -0.1700
Data Index: 446668 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19