Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2566 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.7785. Min Act: -0.1700
Data Index: 3160985 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.7785. Min Act: -0.1700
Data Index: 8080440 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.8097. Min Act: -0.1700
Data Index: 6101228 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.7785. Min Act: -0.1700
Data Index: 3716089 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.7160. Min Act: -0.1700
Data Index: 4008626 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.6535. Min Act: -0.1700
Data Index: 1293370 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.5597. Min Act: -0.1700
Data Index: 4476953 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.5597. Min Act: -0.1700
Data Index: 4212413 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.5597. Min Act: -0.1700
Data Index: 2737514 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.5285. Min Act: -0.1700
Data Index: 8432637 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.5285. Min Act: -0.1700
Data Index: 1671799 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.4972. Min Act: -0.1700
Data Index: 8587575 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.4660. Min Act: -0.1700
Data Index: 868968 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.4660. Min Act: -0.1698
Data Index: 239797 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.4660. Min Act: -0.1700
Data Index: 7439949 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.4660. Min Act: -0.1700
Data Index: 5439625 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.4347. Min Act: -0.1700
Data Index: 5997648 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.4347. Min Act: -0.1700
Data Index: 1340439 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.4660. Min Act: -0.1700
Data Index: 1552395 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8097. Min Range: -4.8097
Max Act: 4.4660. Min Act: -0.1700
Data Index: 7154259 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19