Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0967. Min Range: -6.0967
Max Act: 6.0967. Min Act: -0.1700
Data Index: 5910799 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0967. Min Range: -6.0967
Max Act: 6.0655. Min Act: -0.1700
Data Index: 2807107 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.9405. Min Act: -0.1700
Data Index: 1845632 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.9405. Min Act: -0.1700
Data Index: 8552501 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.8467. Min Act: -0.1700
Data Index: 2222820 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.8467. Min Act: -0.1700
Data Index: 2015906 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.7842. Min Act: -0.1700
Data Index: 7433993 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.7530. Min Act: -0.1700
Data Index: 3023961 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.7842. Min Act: -0.1700
Data Index: 5182220 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.7530. Min Act: -0.1700
Data Index: 3649992 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.7217. Min Act: -0.1700
Data Index: 5995070 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.7217. Min Act: -0.1700
Data Index: 8031293 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.6905. Min Act: -0.1700
Data Index: 6234500 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.6905. Min Act: -0.1700
Data Index: 3649987 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.6905. Min Act: -0.1700
Data Index: 5269930 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.6280. Min Act: -0.1700
Data Index: 3983110 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.6592. Min Act: -0.1700
Data Index: 1606728 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.6592. Min Act: -0.1700
Data Index: 7914393 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.6280. Min Act: -0.1700
Data Index: 2543028 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0967. Min Range: -6.0967
Max Act: 5.6280. Min Act: -0.1700
Data Index: 4947794 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #19