Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2430 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.4618. Min Act: -0.1700
Data Index: 224714 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.3055. Min Act: -0.1700
Data Index: 970783 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.3055. Min Act: -0.1700
Data Index: 2468209 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.2743. Min Act: -0.1700
Data Index: 1716400 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.2430. Min Act: -0.1700
Data Index: 549120 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.2118. Min Act: -0.1700
Data Index: 8308488 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.2118. Min Act: -0.1700
Data Index: 5101367 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.1493. Min Act: -0.1700
Data Index: 3816684 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.0868. Min Act: -0.1700
Data Index: 5893254 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.0868. Min Act: -0.1700
Data Index: 4517585 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4618. Min Range: -7.4618
Max Act: 7.0555. Min Act: -0.1700
Data Index: 6661229 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.9930. Min Act: -0.1700
Data Index: 811097 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.9618. Min Act: -0.1700
Data Index: 4661875 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.9618. Min Act: -0.1700
Data Index: 7147172 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.9618. Min Act: -0.1700
Data Index: 5457564 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.9618. Min Act: -0.1700
Data Index: 8022560 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.9618. Min Act: -0.1700
Data Index: 3737761 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.8993. Min Act: -0.1700
Data Index: 2687758 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.8993. Min Act: -0.1700
Data Index: 1370353 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4618. Min Range: -7.4618
Max Act: 6.8993. Min Act: -0.1700
Data Index: 8277800 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19