Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3562 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.9546. Min Range: -12.9546
Max Act: 12.9546. Min Act: -0.1700
Data Index: 3814061 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.9546. Min Range: -12.9546
Max Act: 12.2046. Min Act: -0.1700
Data Index: 3354228 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.9546. Min Range: -12.9546
Max Act: 12.1421. Min Act: -0.1700
Data Index: 528359 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.9546. Min Range: -12.9546
Max Act: 12.0171. Min Act: -0.1700
Data Index: 3383015 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.9546. Min Range: -12.9546
Max Act: 11.8296. Min Act: -0.1700
Data Index: 3173444 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.9546. Min Range: -12.9546
Max Act: 11.8296. Min Act: -0.1700
Data Index: 2858237 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.9546. Min Range: -12.9546
Max Act: 11.7671. Min Act: -0.1700
Data Index: 6046653 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.9546. Min Range: -12.9546
Max Act: 11.7046. Min Act: -0.1700
Data Index: 6954850 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.9546. Min Range: -12.9546
Max Act: 11.6421. Min Act: -0.1700
Data Index: 8598724 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.9546. Min Range: -12.9546
Max Act: 11.6421. Min Act: -0.1700
Data Index: 8036727 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.9546. Min Range: -12.9546
Max Act: 11.5796. Min Act: -0.1700
Data Index: 4265654 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.9546. Min Range: -12.9546
Max Act: 11.5796. Min Act: -0.1700
Data Index: 3811577 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.9546. Min Range: -12.9546
Max Act: 11.5796. Min Act: -0.1700
Data Index: 2569223 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.9546. Min Range: -12.9546
Max Act: 11.5171. Min Act: -0.1700
Data Index: 2348035 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.9546. Min Range: -12.9546
Max Act: 11.5796. Min Act: -0.1700
Data Index: 3525079 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.9546. Min Range: -12.9546
Max Act: 11.4546. Min Act: -0.1700
Data Index: 2863857 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.9546. Min Range: -12.9546
Max Act: 11.4546. Min Act: -0.1700
Data Index: 3506122 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.9546. Min Range: -12.9546
Max Act: 11.3921. Min Act: -0.1700
Data Index: 5734635 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.9546. Min Range: -12.9546
Max Act: 11.3296. Min Act: -0.1700
Data Index: 6169150 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.9546. Min Range: -12.9546
Max Act: 11.3296. Min Act: -0.1700
Data Index: 6932483 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19