Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5413 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8222. Min Range: -7.8222
Max Act: 7.8222. Min Act: -0.1700
Data Index: 6692523 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8222. Min Range: -7.8222
Max Act: 7.2284. Min Act: -0.1700
Data Index: 1566573 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8222. Min Range: -7.8222
Max Act: 7.1034. Min Act: -0.1700
Data Index: 7655094 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8222. Min Range: -7.8222
Max Act: 7.1034. Min Act: -0.1700
Data Index: 4907034 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8222. Min Range: -7.8222
Max Act: 7.0409. Min Act: -0.1700
Data Index: 5508685 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8222. Min Range: -7.8222
Max Act: 7.0097. Min Act: -0.1700
Data Index: 6315077 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8222. Min Range: -7.8222
Max Act: 7.0409. Min Act: -0.1700
Data Index: 8773381 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8222. Min Range: -7.8222
Max Act: 7.0097. Min Act: -0.1700
Data Index: 3145517 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8222. Min Range: -7.8222
Max Act: 6.9784. Min Act: -0.1700
Data Index: 8722413 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8222. Min Range: -7.8222
Max Act: 6.9472. Min Act: -0.1700
Data Index: 4190604 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8222. Min Range: -7.8222
Max Act: 6.9472. Min Act: -0.1700
Data Index: 7579030 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8222. Min Range: -7.8222
Max Act: 6.9472. Min Act: -0.1700
Data Index: 7346414 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8222. Min Range: -7.8222
Max Act: 6.9159. Min Act: -0.1700
Data Index: 6013124 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8222. Min Range: -7.8222
Max Act: 6.8847. Min Act: -0.1700
Data Index: 5828088 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8222. Min Range: -7.8222
Max Act: 6.8847. Min Act: -0.1700
Data Index: 8770997 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8222. Min Range: -7.8222
Max Act: 6.8847. Min Act: -0.1700
Data Index: 6333694 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8222. Min Range: -7.8222
Max Act: 6.8534. Min Act: -0.1700
Data Index: 633425 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8222. Min Range: -7.8222
Max Act: 6.8222. Min Act: -0.1700
Data Index: 3083017 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8222. Min Range: -7.8222
Max Act: 6.7909. Min Act: -0.1700
Data Index: 7194252 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8222. Min Range: -7.8222
Max Act: 6.8222. Min Act: -0.1700
Data Index: 5510711 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19