Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1238 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.9269. Min Act: -0.1700
Data Index: 833624 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.9110. Min Act: -0.1700
Data Index: 5448275 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.8952. Min Act: -0.1700
Data Index: 7104137 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.8952. Min Act: -0.1700
Data Index: 6863624 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.8634. Min Act: -0.1700
Data Index: 6963712 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.8634. Min Act: -0.1700
Data Index: 4361088 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.8793. Min Act: -0.1700
Data Index: 6152575 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.8317. Min Act: -0.1700
Data Index: 437876 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.8476. Min Act: -0.1700
Data Index: 2618423 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.8317. Min Act: -0.1700
Data Index: 5825984 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.8158. Min Act: -0.1700
Data Index: 5651085 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.8317. Min Act: -0.1700
Data Index: 4596428 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.8158. Min Act: -0.1700
Data Index: 2091492 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.8158. Min Act: -0.1700
Data Index: 6320180 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.7680. Min Act: -0.1700
Data Index: 2628836 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.7839. Min Act: -0.1700
Data Index: 1369430 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.7680. Min Act: -0.1700
Data Index: 526652 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.7680. Min Act: -0.1700
Data Index: 5040578 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.7839. Min Act: -0.1700
Data Index: 1456049 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9269. Min Range: -2.9269
Max Act: 2.7680. Min Act: -0.1700
Data Index: 7761590 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19