Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5170 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.8109. Min Act: -0.1700
Data Index: 8739012 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.7171. Min Act: -0.1700
Data Index: 7070138 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.5921. Min Act: -0.1700
Data Index: 1466723 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.5921. Min Act: -0.1700
Data Index: 7070136 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.5609. Min Act: -0.1700
Data Index: 3472155 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.5296. Min Act: -0.1700
Data Index: 7800620 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.4984. Min Act: -0.1700
Data Index: 7070134 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.4984. Min Act: -0.1700
Data Index: 3361581 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.4984. Min Act: -0.1700
Data Index: 5845728 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.4359. Min Act: -0.1700
Data Index: 7070137 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.4359. Min Act: -0.1700
Data Index: 2093436 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.4046. Min Act: -0.1700
Data Index: 296723 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.3734. Min Act: -0.1700
Data Index: 3361582 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.3734. Min Act: -0.1700
Data Index: 3310781 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.3734. Min Act: -0.1700
Data Index: 1708246 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.3734. Min Act: -0.1700
Data Index: 4966510 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.3421. Min Act: -0.1700
Data Index: 71821 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.3421. Min Act: -0.1700
Data Index: 2634365 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.3109. Min Act: -0.1700
Data Index: 2562157 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8109. Min Range: -6.8109
Max Act: 6.3421. Min Act: -0.1700
Data Index: 8053924 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #19