Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1682 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.8645. Min Act: -0.1700
Data Index: 536610 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.8332. Min Act: -0.1700
Data Index: 2894656 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.8020. Min Act: -0.1700
Data Index: 8335599 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.7707. Min Act: -0.1700
Data Index: 254740 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.7707. Min Act: -0.1700
Data Index: 4620468 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.8020. Min Act: -0.1700
Data Index: 3950130 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.7707. Min Act: -0.1700
Data Index: 6742316 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.7707. Min Act: -0.1700
Data Index: 8674956 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.7394. Min Act: -0.1700
Data Index: 2727173 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.7394. Min Act: -0.1700
Data Index: 8462207 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.7081. Min Act: -0.1700
Data Index: 6269592 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.6768. Min Act: -0.1700
Data Index: 6277005 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.6768. Min Act: -0.1700
Data Index: 3439807 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.6768. Min Act: -0.1700
Data Index: 2149736 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.6299. Min Act: -0.1700
Data Index: 3693938 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.6299. Min Act: -0.1700
Data Index: 1860674 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.6455. Min Act: -0.1700
Data Index: 36021 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.5986. Min Act: -0.1700
Data Index: 1576432 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.6143. Min Act: -0.1700
Data Index: 4997891 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8645. Min Range: -3.8645
Max Act: 3.5829. Min Act: -0.1700
Data Index: 7081598 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19