Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5340 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4781. Min Range: -9.4781
Max Act: 9.4781. Min Act: -0.1700
Data Index: 8596718 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4781. Min Range: -9.4781
Max Act: 9.3531. Min Act: -0.1700
Data Index: 1069439 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4781. Min Range: -9.4781
Max Act: 9.3531. Min Act: -0.1700
Data Index: 7380426 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4781. Min Range: -9.4781
Max Act: 9.2281. Min Act: -0.1700
Data Index: 6179667 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4781. Min Range: -9.4781
Max Act: 8.9781. Min Act: -0.1700
Data Index: 8084336 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4781. Min Range: -9.4781
Max Act: 8.8531. Min Act: -0.1700
Data Index: 2745384 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4781. Min Range: -9.4781
Max Act: 8.8531. Min Act: -0.1700
Data Index: 554250 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4781. Min Range: -9.4781
Max Act: 8.8531. Min Act: -0.1700
Data Index: 8790746 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4781. Min Range: -9.4781
Max Act: 8.8531. Min Act: -0.1700
Data Index: 6155371 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4781. Min Range: -9.4781
Max Act: 8.7281. Min Act: -0.1700
Data Index: 68824 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4781. Min Range: -9.4781
Max Act: 8.7281. Min Act: -0.1700
Data Index: 2430368 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4781. Min Range: -9.4781
Max Act: 8.7281. Min Act: -0.1700
Data Index: 4777358 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4781. Min Range: -9.4781
Max Act: 8.6656. Min Act: -0.1700
Data Index: 7776663 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4781. Min Range: -9.4781
Max Act: 8.6656. Min Act: -0.1700
Data Index: 728126 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4781. Min Range: -9.4781
Max Act: 8.6656. Min Act: -0.1700
Data Index: 5723940 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4781. Min Range: -9.4781
Max Act: 8.6656. Min Act: -0.1700
Data Index: 2859882 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4781. Min Range: -9.4781
Max Act: 8.6656. Min Act: -0.1700
Data Index: 2170702 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4781. Min Range: -9.4781
Max Act: 8.6031. Min Act: -0.1700
Data Index: 7048967 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4781. Min Range: -9.4781
Max Act: 8.6031. Min Act: -0.1700
Data Index: 4063967 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4781. Min Range: -9.4781
Max Act: 8.6031. Min Act: -0.1700
Data Index: 17301 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19