Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2860 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.9253. Min Act: -0.1700
Data Index: 7188104 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.9083. Min Act: -0.1700
Data Index: 3808005 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8912. Min Act: -0.1700
Data Index: 1557695 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8742. Min Act: -0.1700
Data Index: 1980447 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8571. Min Act: -0.1700
Data Index: 5506643 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8571. Min Act: -0.1700
Data Index: 4123588 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8571. Min Act: -0.1700
Data Index: 5117883 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8399. Min Act: -0.1700
Data Index: 1992522 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8399. Min Act: -0.1700
Data Index: 7757022 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8399. Min Act: -0.1590
Data Index: 4909335 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8399. Min Act: -0.1700
Data Index: 380402 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8399. Min Act: -0.1700
Data Index: 7054051 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8399. Min Act: -0.1664
Data Index: 4909321 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8399. Min Act: -0.1700
Data Index: 6380941 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8399. Min Act: -0.1699
Data Index: 8285082 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8399. Min Act: -0.1700
Data Index: 5814887 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8399. Min Act: -0.1700
Data Index: 175481 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8228. Min Act: -0.1672
Data Index: 8260077 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8056. Min Act: -0.1700
Data Index: 414815 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9253. Min Range: -1.9253
Max Act: 1.8056. Min Act: -0.1700
Data Index: 3153479 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19