Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3054 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0928. Min Range: -12.0928
Max Act: 12.0928. Min Act: -0.1700
Data Index: 1689010 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.9053. Min Act: -0.1700
Data Index: 4971666 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.5928. Min Act: -0.1700
Data Index: 2774941 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.4053. Min Act: -0.1700
Data Index: 8461545 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.3428. Min Act: -0.1700
Data Index: 3320558 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.4053. Min Act: -0.1700
Data Index: 481706 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.2178. Min Act: -0.1700
Data Index: 1052428 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.1553. Min Act: -0.1700
Data Index: 651458 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.1553. Min Act: -0.1700
Data Index: 3990258 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.1553. Min Act: -0.1700
Data Index: 387877 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.1553. Min Act: -0.1700
Data Index: 7571968 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.1553. Min Act: -0.1700
Data Index: 1372384 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.0928. Min Act: -0.1700
Data Index: 2797828 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.0928. Min Act: -0.1700
Data Index: 5840339 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.0928. Min Act: -0.1700
Data Index: 6603245 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.0928. Min Act: -0.1700
Data Index: 8314635 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.0303. Min Act: -0.1700
Data Index: 4658198 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.0303. Min Act: -0.1700
Data Index: 4920770 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.0303. Min Act: -0.1700
Data Index: 1817711 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0928. Min Range: -12.0928
Max Act: 11.0303. Min Act: -0.1700
Data Index: 1388864 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #19