Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2472 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0066. Min Range: -3.0066
Max Act: 3.0066. Min Act: -0.1700
Data Index: 338479 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.9749. Min Act: -0.1700
Data Index: 4843343 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.9749. Min Act: -0.1700
Data Index: 5843976 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.9749. Min Act: -0.1700
Data Index: 8066244 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.9749. Min Act: -0.1700
Data Index: 5873717 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.9749. Min Act: -0.1700
Data Index: 5465765 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.9749. Min Act: -0.1700
Data Index: 4548136 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.9749. Min Act: -0.1700
Data Index: 1638298 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.9433. Min Act: -0.1700
Data Index: 7291704 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.9116. Min Act: -0.1700
Data Index: 163810 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.8799. Min Act: -0.1700
Data Index: 967926 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.8481. Min Act: -0.1700
Data Index: 5174181 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.8799. Min Act: -0.1700
Data Index: 5798832 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.8481. Min Act: -0.1700
Data Index: 1998508 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.8322. Min Act: -0.1700
Data Index: 6128954 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.8481. Min Act: -0.1700
Data Index: 8576982 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.8481. Min Act: -0.1700
Data Index: 5330661 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.8481. Min Act: -0.1700
Data Index: 537784 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.8481. Min Act: -0.1700
Data Index: 6396675 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0066. Min Range: -3.0066
Max Act: 2.8163. Min Act: -0.1700
Data Index: 7526094 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19