Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3250 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.3020. Min Act: -0.1700
Data Index: 2020554 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.2707. Min Act: -0.1700
Data Index: 5678425 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.2082. Min Act: -0.1700
Data Index: 6054987 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.0832. Min Act: -0.1700
Data Index: 3840466 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.1145. Min Act: -0.1700
Data Index: 6054984 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.0832. Min Act: -0.1700
Data Index: 592773 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.0832. Min Act: -0.1700
Data Index: 2020547 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.0832. Min Act: -0.1700
Data Index: 3257041 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.0520. Min Act: -0.1700
Data Index: 8380996 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.0832. Min Act: -0.1700
Data Index: 4078529 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.0520. Min Act: -0.1700
Data Index: 3909404 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.0520. Min Act: -0.1700
Data Index: 2280179 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.0520. Min Act: -0.1700
Data Index: 3833436 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.0832. Min Act: -0.1700
Data Index: 6054991 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.0520. Min Act: -0.1700
Data Index: 1616354 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.0520. Min Act: -0.1700
Data Index: 6043421 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.0207. Min Act: -0.1700
Data Index: 6652285 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.0207. Min Act: -0.1700
Data Index: 6599099 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3020. Min Range: -6.3020
Max Act: 6.0207. Min Act: -0.1700
Data Index: 4587387 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3020. Min Range: -6.3020
Max Act: 5.9895. Min Act: -0.1700
Data Index: 4995642 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19