Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2907 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.7333. Min Act: -0.1700
Data Index: 423339 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.6813. Min Act: -0.1700
Data Index: 7322192 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.6727. Min Act: -0.1700
Data Index: 5095267 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.6640. Min Act: -0.1700
Data Index: 4711712 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.6466. Min Act: -0.1700
Data Index: 8104537 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.6466. Min Act: -0.1700
Data Index: 7344614 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.6291. Min Act: -0.1700
Data Index: 5402976 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.6204. Min Act: -0.1700
Data Index: 8596156 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.6379. Min Act: -0.1700
Data Index: 8754981 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.6291. Min Act: -0.1700
Data Index: 7290507 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.6204. Min Act: -0.1700
Data Index: 3111356 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.6204. Min Act: -0.1700
Data Index: 7311753 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.6117. Min Act: -0.1700
Data Index: 8702985 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.6204. Min Act: -0.1700
Data Index: 6445225 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.6030. Min Act: -0.1700
Data Index: 363767 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.6117. Min Act: -0.1700
Data Index: 3930270 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.5855. Min Act: -0.1699
Data Index: 562126 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.5855. Min Act: -0.1700
Data Index: 6403900 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.5855. Min Act: -0.1700
Data Index: 8300465 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7333. Min Range: -1.7333
Max Act: 1.5942. Min Act: -0.1700
Data Index: 3338906 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19