Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4318 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.2373. Min Act: -0.1700
Data Index: 6054128 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.2061. Min Act: -0.1699
Data Index: 6477749 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.1748. Min Act: -0.1700
Data Index: 669784 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.1436. Min Act: -0.1700
Data Index: 468639 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.1123. Min Act: -0.1697
Data Index: 8196917 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.1123. Min Act: -0.1700
Data Index: 8642036 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.1123. Min Act: -0.1700
Data Index: 1034351 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.0811. Min Act: -0.1700
Data Index: 2419389 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.0498. Min Act: -0.1700
Data Index: 8740149 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.0811. Min Act: -0.1700
Data Index: 520599 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.0811. Min Act: -0.1700
Data Index: 7816799 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.0811. Min Act: -0.1700
Data Index: 6981929 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.0498. Min Act: -0.1697
Data Index: 6974298 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.0811. Min Act: -0.1700
Data Index: 76041 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.0811. Min Act: -0.1697
Data Index: 5823667 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.0811. Min Act: -0.1700
Data Index: 5302045 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.0811. Min Act: -0.1700
Data Index: 3811319 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.0498. Min Act: -0.1700
Data Index: 601514 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.0498. Min Act: -0.1700
Data Index: 1208040 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2373. Min Range: -5.2373
Max Act: 5.0498. Min Act: -0.1700
Data Index: 932447 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19