Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 670 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.8791. Min Act: -0.1700
Data Index: 1588391 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.7854. Min Act: -0.1700
Data Index: 6100810 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.7229. Min Act: -0.1700
Data Index: 2878185 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.6916. Min Act: -0.1700
Data Index: 5554015 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.6604. Min Act: -0.1700
Data Index: 7819190 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.6291. Min Act: -0.1700
Data Index: 2395790 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.5979. Min Act: -0.1700
Data Index: 1438581 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.6291. Min Act: -0.1700
Data Index: 4607592 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.6291. Min Act: -0.1700
Data Index: 1809529 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.6291. Min Act: -0.1700
Data Index: 3922161 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.5979. Min Act: -0.1700
Data Index: 1125409 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.5979. Min Act: -0.1700
Data Index: 7178485 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.5666. Min Act: -0.1700
Data Index: 2656531 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.5666. Min Act: -0.1700
Data Index: 8482759 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.5979. Min Act: -0.1700
Data Index: 7648280 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.5666. Min Act: -0.1700
Data Index: 5882844 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.5666. Min Act: -0.1700
Data Index: 1862215 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.5666. Min Act: -0.1700
Data Index: 7787012 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.5979. Min Act: -0.1700
Data Index: 5417531 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8791. Min Range: -4.8791
Max Act: 4.5354. Min Act: -0.1700
Data Index: 5697803 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19