Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4937 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.4781. Min Act: -0.1700
Data Index: 4740415 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.2281. Min Act: -0.1700
Data Index: 6100356 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.1656. Min Act: -0.1700
Data Index: 7052105 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.1656. Min Act: -0.1700
Data Index: 2293621 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.1656. Min Act: -0.1700
Data Index: 6392319 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.0719. Min Act: -0.1700
Data Index: 7518578 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.0719. Min Act: -0.1700
Data Index: 7787139 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.0719. Min Act: -0.1700
Data Index: 774341 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.0719. Min Act: -0.1700
Data Index: 7724914 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.0406. Min Act: -0.1700
Data Index: 7321012 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.0719. Min Act: -0.1700
Data Index: 7426597 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.0406. Min Act: -0.1700
Data Index: 8694192 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4781. Min Range: -6.4781
Max Act: 6.0406. Min Act: -0.1700
Data Index: 999617 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4781. Min Range: -6.4781
Max Act: 5.9781. Min Act: -0.1700
Data Index: 6389283 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4781. Min Range: -6.4781
Max Act: 5.9781. Min Act: -0.1700
Data Index: 180934 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4781. Min Range: -6.4781
Max Act: 5.9469. Min Act: -0.1700
Data Index: 5542602 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4781. Min Range: -6.4781
Max Act: 5.9469. Min Act: -0.1700
Data Index: 6687186 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4781. Min Range: -6.4781
Max Act: 5.9469. Min Act: -0.1700
Data Index: 3325693 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4781. Min Range: -6.4781
Max Act: 5.9469. Min Act: -0.1700
Data Index: 7571843 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4781. Min Range: -6.4781
Max Act: 5.9156. Min Act: -0.1700
Data Index: 1204094 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19