Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2988 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.8476. Min Act: -0.1700
Data Index: 106636 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.7851. Min Act: -0.1700
Data Index: 8069641 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.7226. Min Act: -0.1700
Data Index: 6102720 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.7539. Min Act: -0.1700
Data Index: 100385 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.7226. Min Act: -0.1700
Data Index: 2353097 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.6914. Min Act: -0.1700
Data Index: 4524522 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.6289. Min Act: -0.1700
Data Index: 2312517 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.5976. Min Act: -0.1700
Data Index: 3725984 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.5976. Min Act: -0.1700
Data Index: 6441679 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.5664. Min Act: -0.1700
Data Index: 2252145 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.5664. Min Act: -0.1700
Data Index: 4036087 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.5664. Min Act: -0.1700
Data Index: 7453957 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.5664. Min Act: -0.1700
Data Index: 1954503 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.5664. Min Act: -0.1700
Data Index: 8244840 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.5664. Min Act: -0.1700
Data Index: 2684017 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.5664. Min Act: -0.1700
Data Index: 1025145 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.5351. Min Act: -0.1700
Data Index: 3625345 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.5351. Min Act: -0.1700
Data Index: 126224 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.5351. Min Act: -0.1700
Data Index: 4670074 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8476. Min Range: -6.8476
Max Act: 6.5351. Min Act: -0.1700
Data Index: 1687088 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19