Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3342. Min Range: -7.3342
Max Act: 7.3342. Min Act: -0.1700
Data Index: 3793458 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3342. Min Range: -7.3342
Max Act: 7.1154. Min Act: -0.1700
Data Index: 261542 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3342. Min Range: -7.3342
Max Act: 7.0842. Min Act: -0.1700
Data Index: 1103589 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3342. Min Range: -7.3342
Max Act: 7.0217. Min Act: -0.1700
Data Index: 6658811 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3342. Min Range: -7.3342
Max Act: 6.9904. Min Act: -0.1700
Data Index: 6334916 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3342. Min Range: -7.3342
Max Act: 6.9279. Min Act: -0.1700
Data Index: 8825565 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3342. Min Range: -7.3342
Max Act: 6.9592. Min Act: -0.1700
Data Index: 1593034 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3342. Min Range: -7.3342
Max Act: 6.8967. Min Act: -0.1700
Data Index: 768927 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3342. Min Range: -7.3342
Max Act: 6.8654. Min Act: -0.1700
Data Index: 3154836 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3342. Min Range: -7.3342
Max Act: 6.8342. Min Act: -0.1700
Data Index: 4288846 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3342. Min Range: -7.3342
Max Act: 6.8342. Min Act: -0.1700
Data Index: 505988 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3342. Min Range: -7.3342
Max Act: 6.8654. Min Act: -0.1700
Data Index: 8667442 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3342. Min Range: -7.3342
Max Act: 6.7717. Min Act: -0.1700
Data Index: 4387506 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3342. Min Range: -7.3342
Max Act: 6.7717. Min Act: -0.1700
Data Index: 6183437 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3342. Min Range: -7.3342
Max Act: 6.7717. Min Act: -0.1700
Data Index: 2245742 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3342. Min Range: -7.3342
Max Act: 6.8029. Min Act: -0.1700
Data Index: 8634190 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3342. Min Range: -7.3342
Max Act: 6.7404. Min Act: -0.1700
Data Index: 3514828 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3342. Min Range: -7.3342
Max Act: 6.7404. Min Act: -0.1700
Data Index: 5487662 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3342. Min Range: -7.3342
Max Act: 6.6467. Min Act: -0.1700
Data Index: 8421637 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3342. Min Range: -7.3342
Max Act: 6.6779. Min Act: -0.1700
Data Index: 2371175 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19