Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2049 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.9019. Min Act: -0.1700
Data Index: 4975505 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.7612. Min Act: -0.1700
Data Index: 3513725 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.7142. Min Act: -0.1700
Data Index: 7000435 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.7142. Min Act: -0.1700
Data Index: 726231 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.7612. Min Act: -0.1700
Data Index: 6735401 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.6986. Min Act: -0.1700
Data Index: 884720 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.7142. Min Act: -0.1700
Data Index: 4102408 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.6673. Min Act: -0.1700
Data Index: 7266416 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.6517. Min Act: -0.1700
Data Index: 6556555 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.6673. Min Act: -0.1700
Data Index: 5697656 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.6673. Min Act: -0.1700
Data Index: 6556554 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.6673. Min Act: -0.1700
Data Index: 2699478 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.6517. Min Act: -0.1700
Data Index: 4034919 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.6673. Min Act: -0.1700
Data Index: 8139470 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.6517. Min Act: -0.1700
Data Index: 177980 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.6204. Min Act: -0.1700
Data Index: 5296115 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.6204. Min Act: -0.1700
Data Index: 706144 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.6047. Min Act: -0.1700
Data Index: 5850263 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.6360. Min Act: -0.1700
Data Index: 5659861 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9019. Min Range: -3.9019
Max Act: 3.6360. Min Act: -0.1700
Data Index: 500494 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19