Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 172 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.8057. Min Act: -0.1700
Data Index: 3729367 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.7579. Min Act: -0.1700
Data Index: 8220410 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.7260. Min Act: -0.1700
Data Index: 2715656 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.7100. Min Act: -0.1700
Data Index: 4315301 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.7100. Min Act: -0.1700
Data Index: 6236987 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.6940. Min Act: -0.1700
Data Index: 7603868 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.6619. Min Act: -0.1700
Data Index: 7997005 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.6459. Min Act: -0.1700
Data Index: 100004 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.6459. Min Act: -0.1700
Data Index: 3183047 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.6298. Min Act: -0.1700
Data Index: 7841286 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.6298. Min Act: -0.1700
Data Index: 3980457 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.6298. Min Act: -0.1700
Data Index: 5744215 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.6298. Min Act: -0.1700
Data Index: 1194669 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.6138. Min Act: -0.1700
Data Index: 8658197 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.6138. Min Act: -0.1700
Data Index: 4786694 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.6138. Min Act: -0.1700
Data Index: 7695302 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.5977. Min Act: -0.1700
Data Index: 6453008 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.5977. Min Act: -0.1700
Data Index: 2994499 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.6138. Min Act: -0.1700
Data Index: 1018060 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8057. Min Range: -2.8057
Max Act: 2.5977. Min Act: -0.1700
Data Index: 8330103 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19