Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4699 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.9532. Min Act: -0.1700
Data Index: 7471754 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.8282. Min Act: -0.1700
Data Index: 406775 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.7657. Min Act: -0.1700
Data Index: 5897075 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.6095. Min Act: -0.1700
Data Index: 5759930 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.6095. Min Act: -0.1700
Data Index: 2728474 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.4220. Min Act: -0.1700
Data Index: 4821894 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.3907. Min Act: -0.1700
Data Index: 4338116 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.3907. Min Act: -0.1700
Data Index: 7443406 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.3907. Min Act: -0.1700
Data Index: 5536580 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.3595. Min Act: -0.1700
Data Index: 7805102 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.3282. Min Act: -0.1700
Data Index: 5948888 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.3282. Min Act: -0.1700
Data Index: 2297771 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.2970. Min Act: -0.1700
Data Index: 6643998 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.2657. Min Act: -0.1700
Data Index: 5716638 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.2657. Min Act: -0.1700
Data Index: 7301995 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.2657. Min Act: -0.1700
Data Index: 6314121 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.2657. Min Act: -0.1700
Data Index: 2046547 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.2032. Min Act: -0.1700
Data Index: 8487439 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.2032. Min Act: -0.1700
Data Index: 7206656 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9532. Min Range: -6.9532
Max Act: 6.1407. Min Act: -0.1700
Data Index: 5816558 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19