Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3049 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.8723. Min Act: -0.1700
Data Index: 7093838 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.7473. Min Act: -0.1700
Data Index: 4876793 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.7473. Min Act: -0.1700
Data Index: 2608603 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.7161. Min Act: -0.1700
Data Index: 7410449 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6848. Min Act: -0.1700
Data Index: 3143231 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6536. Min Act: -0.1700
Data Index: 3539173 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6848. Min Act: -0.1700
Data Index: 4323469 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6536. Min Act: -0.1700
Data Index: 614457 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6536. Min Act: -0.1700
Data Index: 1191372 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6536. Min Act: -0.1700
Data Index: 7092885 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6223. Min Act: -0.1700
Data Index: 320672 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6536. Min Act: -0.1700
Data Index: 2779754 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6223. Min Act: -0.1700
Data Index: 4256384 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.5911. Min Act: -0.1700
Data Index: 1604044 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.5911. Min Act: -0.1700
Data Index: 3402450 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.5911. Min Act: -0.1700
Data Index: 1604042 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.5911. Min Act: -0.1700
Data Index: 8775876 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.6223. Min Act: -0.1700
Data Index: 4018294 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.5598. Min Act: -0.1700
Data Index: 1849610 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8723. Min Range: -5.8723
Max Act: 5.5598. Min Act: -0.1700
Data Index: 3389973 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19