Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3644 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0992. Min Range: -6.0992
Max Act: 6.0992. Min Act: -0.1700
Data Index: 4534564 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0992. Min Range: -6.0992
Max Act: 6.0367. Min Act: -0.1700
Data Index: 4792894 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.9117. Min Act: -0.1700
Data Index: 5788729 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.9117. Min Act: -0.1700
Data Index: 7239802 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.8805. Min Act: -0.1700
Data Index: 7610623 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.8805. Min Act: -0.1700
Data Index: 8386944 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.8805. Min Act: -0.1700
Data Index: 18315 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.8492. Min Act: -0.1700
Data Index: 3946647 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.8180. Min Act: -0.1700
Data Index: 67575 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.7867. Min Act: -0.1700
Data Index: 8734847 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.8180. Min Act: -0.1700
Data Index: 5884223 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.7555. Min Act: -0.1700
Data Index: 4260229 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.7555. Min Act: -0.1700
Data Index: 7713189 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.7555. Min Act: -0.1700
Data Index: 2892664 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.7242. Min Act: -0.1700
Data Index: 6168022 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.7242. Min Act: -0.1700
Data Index: 8439105 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.7242. Min Act: -0.1700
Data Index: 6938053 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.6617. Min Act: -0.1700
Data Index: 5184028 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.6930. Min Act: -0.1700
Data Index: 4711651 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0992. Min Range: -6.0992
Max Act: 5.6930. Min Act: -0.1700
Data Index: 7753333 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19