Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 887 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.9051. Min Act: -0.1700
Data Index: 8384419 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.8426. Min Act: -0.1700
Data Index: 6800346 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.7800. Min Act: -0.1700
Data Index: 7646804 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.7800. Min Act: -0.1700
Data Index: 3165005 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.7488. Min Act: -0.1700
Data Index: 3335348 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.7175. Min Act: -0.1700
Data Index: 5631208 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.7175. Min Act: -0.1700
Data Index: 8522778 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.7175. Min Act: -0.1700
Data Index: 3284844 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.7175. Min Act: -0.1700
Data Index: 1907510 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.7175. Min Act: -0.1700
Data Index: 6983620 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.7175. Min Act: -0.1700
Data Index: 488314 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.6862. Min Act: -0.1700
Data Index: 3383862 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.6862. Min Act: -0.1700
Data Index: 7302784 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.6549. Min Act: -0.1700
Data Index: 6964370 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.6549. Min Act: -0.1700
Data Index: 8688288 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.6549. Min Act: -0.1700
Data Index: 7768779 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.6549. Min Act: -0.1700
Data Index: 1418002 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.6549. Min Act: -0.1700
Data Index: 1817073 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.6549. Min Act: -0.1700
Data Index: 3700085 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9051. Min Range: -3.9051
Max Act: 3.6549. Min Act: -0.1700
Data Index: 256616 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19