Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3146 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4984. Min Act: -0.1700
Data Index: 2270662 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4660. Min Act: -0.1700
Data Index: 8409843 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4660. Min Act: -0.1700
Data Index: 3997119 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4497. Min Act: -0.1700
Data Index: 2270661 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4497. Min Act: -0.1700
Data Index: 8659864 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4335. Min Act: -0.1700
Data Index: 3953226 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4497. Min Act: -0.1700
Data Index: 3609119 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4172. Min Act: -0.1700
Data Index: 3291144 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4172. Min Act: -0.1700
Data Index: 2685636 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4009. Min Act: -0.1700
Data Index: 446146 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4009. Min Act: -0.1700
Data Index: 203883 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4335. Min Act: -0.1700
Data Index: 1864763 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4335. Min Act: -0.1700
Data Index: 137673 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4009. Min Act: -0.1700
Data Index: 5910128 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.3845. Min Act: -0.1700
Data Index: 8350794 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4009. Min Act: -0.1700
Data Index: 7596192 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.3845. Min Act: -0.1700
Data Index: 278941 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4009. Min Act: -0.1700
Data Index: 6628674 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.3845. Min Act: -0.1700
Data Index: 1760718 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4984. Min Range: -2.4984
Max Act: 2.4009. Min Act: -0.1700
Data Index: 479184 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19