Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2458 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.2359. Min Act: -0.1700
Data Index: 3402493 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.2359. Min Act: -0.1700
Data Index: 4154082 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.2359. Min Act: -0.1700
Data Index: 658406 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.2359. Min Act: -0.1700
Data Index: 3383875 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.2359. Min Act: -0.1697
Data Index: 1353579 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.2359. Min Act: -0.1700
Data Index: 4462078 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.2359. Min Act: -0.1700
Data Index: 878085 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.2046. Min Act: -0.1700
Data Index: 3018758 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.2046. Min Act: -0.1700
Data Index: 939468 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1734. Min Act: -0.1700
Data Index: 1248502 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1734. Min Act: -0.1696
Data Index: 998194 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1734. Min Act: -0.1700
Data Index: 3495461 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1109. Min Act: -0.1700
Data Index: 5163190 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1421. Min Act: -0.1699
Data Index: 3041211 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1421. Min Act: -0.1700
Data Index: 3123729 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1734. Min Act: -0.1700
Data Index: 7210332 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1421. Min Act: -0.1700
Data Index: 5216477 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1109. Min Act: -0.1700
Data Index: 733814 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1109. Min Act: -0.1700
Data Index: 4509495 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2359. Min Range: -5.2359
Max Act: 5.1109. Min Act: -0.1700
Data Index: 508774 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19