Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2983 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0055. Min Range: -7.0055
Max Act: 7.0055. Min Act: -0.1700
Data Index: 6197628 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.8180. Min Act: -0.1700
Data Index: 7880945 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.7868. Min Act: -0.1700
Data Index: 2261330 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.7243. Min Act: -0.1700
Data Index: 7331241 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.6618. Min Act: -0.1700
Data Index: 4623840 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.6305. Min Act: -0.1700
Data Index: 5488850 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.5993. Min Act: -0.1700
Data Index: 4182878 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.5680. Min Act: -0.1700
Data Index: 2147527 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.5993. Min Act: -0.1700
Data Index: 6716570 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.5368. Min Act: -0.1700
Data Index: 3147179 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.5368. Min Act: -0.1700
Data Index: 5403712 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.5368. Min Act: -0.1700
Data Index: 5219968 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.5055. Min Act: -0.1700
Data Index: 2932822 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.5055. Min Act: -0.1700
Data Index: 619135 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.5055. Min Act: -0.1700
Data Index: 6113051 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.5055. Min Act: -0.1700
Data Index: 1257515 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.4743. Min Act: -0.1700
Data Index: 2517775 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.4743. Min Act: -0.1700
Data Index: 4269926 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.4118. Min Act: -0.1700
Data Index: 3462317 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0055. Min Range: -7.0055
Max Act: 6.4118. Min Act: -0.1700
Data Index: 6289182 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #19