Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3573 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9892. Min Range: -9.9892
Max Act: 9.9892. Min Act: -0.1700
Data Index: 4736609 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9892. Min Range: -9.9892
Max Act: 9.0517. Min Act: -0.1700
Data Index: 2221949 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9892. Min Range: -9.9892
Max Act: 9.0517. Min Act: -0.1700
Data Index: 3113964 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9892. Min Range: -9.9892
Max Act: 9.0517. Min Act: -0.1700
Data Index: 6261524 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9892. Min Range: -9.9892
Max Act: 8.8642. Min Act: -0.1700
Data Index: 7176781 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9892. Min Range: -9.9892
Max Act: 8.7392. Min Act: -0.1700
Data Index: 7560169 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9892. Min Range: -9.9892
Max Act: 8.7392. Min Act: -0.1700
Data Index: 4420413 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9892. Min Range: -9.9892
Max Act: 8.7392. Min Act: -0.1700
Data Index: 2342372 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9892. Min Range: -9.9892
Max Act: 8.7392. Min Act: -0.1700
Data Index: 2111452 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9892. Min Range: -9.9892
Max Act: 8.6767. Min Act: -0.1700
Data Index: 2988692 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9892. Min Range: -9.9892
Max Act: 8.6142. Min Act: -0.1700
Data Index: 7476892 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9892. Min Range: -9.9892
Max Act: 8.6142. Min Act: -0.1700
Data Index: 3014354 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9892. Min Range: -9.9892
Max Act: 8.6142. Min Act: -0.1700
Data Index: 6433878 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9892. Min Range: -9.9892
Max Act: 8.6142. Min Act: -0.1700
Data Index: 6680402 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9892. Min Range: -9.9892
Max Act: 8.5517. Min Act: -0.1700
Data Index: 7301361 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9892. Min Range: -9.9892
Max Act: 8.5517. Min Act: -0.1700
Data Index: 8731818 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9892. Min Range: -9.9892
Max Act: 8.4892. Min Act: -0.1700
Data Index: 1473998 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9892. Min Range: -9.9892
Max Act: 8.4892. Min Act: -0.1700
Data Index: 3960367 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9892. Min Range: -9.9892
Max Act: 8.4892. Min Act: -0.1700
Data Index: 3388030 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9892. Min Range: -9.9892
Max Act: 8.4892. Min Act: -0.1700
Data Index: 5422380 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19