Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8847. Min Range: -10.8847
Max Act: 10.8847. Min Act: -0.1700
Data Index: 5192991 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8847. Min Range: -10.8847
Max Act: 10.0722. Min Act: -0.1700
Data Index: 717637 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8847. Min Range: -10.8847
Max Act: 10.0722. Min Act: -0.1700
Data Index: 745584 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8847. Min Range: -10.8847
Max Act: 10.0097. Min Act: -0.1700
Data Index: 596943 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8847. Min Range: -10.8847
Max Act: 9.9472. Min Act: -0.1700
Data Index: 787791 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8847. Min Range: -10.8847
Max Act: 9.9472. Min Act: -0.1700
Data Index: 7076060 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8847. Min Range: -10.8847
Max Act: 9.8847. Min Act: -0.1700
Data Index: 3160523 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8847. Min Range: -10.8847
Max Act: 9.7597. Min Act: -0.1700
Data Index: 1503211 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8847. Min Range: -10.8847
Max Act: 9.6972. Min Act: -0.1700
Data Index: 2366918 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8847. Min Range: -10.8847
Max Act: 9.6347. Min Act: -0.1700
Data Index: 7076062 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8847. Min Range: -10.8847
Max Act: 9.6347. Min Act: -0.1700
Data Index: 1741820 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8847. Min Range: -10.8847
Max Act: 9.6347. Min Act: -0.1700
Data Index: 2366920 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8847. Min Range: -10.8847
Max Act: 9.6347. Min Act: -0.1700
Data Index: 2956171 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8847. Min Range: -10.8847
Max Act: 9.5722. Min Act: -0.1700
Data Index: 7076064 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8847. Min Range: -10.8847
Max Act: 9.5097. Min Act: -0.1700
Data Index: 2563917 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8847. Min Range: -10.8847
Max Act: 9.5097. Min Act: -0.1700
Data Index: 4792648 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8847. Min Range: -10.8847
Max Act: 9.4472. Min Act: -0.1700
Data Index: 7951486 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8847. Min Range: -10.8847
Max Act: 9.3847. Min Act: -0.1700
Data Index: 222831 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8847. Min Range: -10.8847
Max Act: 9.2597. Min Act: -0.1700
Data Index: 6588319 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8847. Min Range: -10.8847
Max Act: 9.2597. Min Act: -0.1700
Data Index: 1690848 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19