Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2497 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6108. Min Range: -7.6108
Max Act: 7.6108. Min Act: -0.1700
Data Index: 2520341 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6108. Min Range: -7.6108
Max Act: 7.2046. Min Act: -0.1700
Data Index: 4192778 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6108. Min Range: -7.6108
Max Act: 7.0483. Min Act: -0.1700
Data Index: 7946863 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6108. Min Range: -7.6108
Max Act: 7.0483. Min Act: -0.1700
Data Index: 2301043 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6108. Min Range: -7.6108
Max Act: 7.0483. Min Act: -0.1700
Data Index: 3288304 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6108. Min Range: -7.6108
Max Act: 7.0171. Min Act: -0.1700
Data Index: 4833323 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6108. Min Range: -7.6108
Max Act: 6.9858. Min Act: -0.1700
Data Index: 3198451 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6108. Min Range: -7.6108
Max Act: 6.9546. Min Act: -0.1700
Data Index: 8300905 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6108. Min Range: -7.6108
Max Act: 6.9546. Min Act: -0.1700
Data Index: 4386410 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6108. Min Range: -7.6108
Max Act: 6.9233. Min Act: -0.1700
Data Index: 7948905 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6108. Min Range: -7.6108
Max Act: 6.9233. Min Act: -0.1700
Data Index: 4003357 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6108. Min Range: -7.6108
Max Act: 6.8608. Min Act: -0.1700
Data Index: 2471020 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6108. Min Range: -7.6108
Max Act: 6.8608. Min Act: -0.1700
Data Index: 7110616 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6108. Min Range: -7.6108
Max Act: 6.8296. Min Act: -0.1700
Data Index: 7931006 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6108. Min Range: -7.6108
Max Act: 6.8296. Min Act: -0.1700
Data Index: 5280694 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6108. Min Range: -7.6108
Max Act: 6.8296. Min Act: -0.1700
Data Index: 928992 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6108. Min Range: -7.6108
Max Act: 6.8608. Min Act: -0.1700
Data Index: 3656300 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6108. Min Range: -7.6108
Max Act: 6.7671. Min Act: -0.1700
Data Index: 3965449 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6108. Min Range: -7.6108
Max Act: 6.7358. Min Act: -0.1700
Data Index: 895919 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6108. Min Range: -7.6108
Max Act: 6.7358. Min Act: -0.1700
Data Index: 5318138 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19