Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 77 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.5012. Min Act: -0.1700
Data Index: 383446 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.5012. Min Act: -0.1700
Data Index: 834945 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.4850. Min Act: -0.1700
Data Index: 270998 (C4 (Web Text))
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.4363. Min Act: -0.1700
Data Index: 1603844 (Python Code)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.4200. Min Act: -0.1700
Data Index: 558167 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.4363. Min Act: -0.1700
Data Index: 1577442 (Python Code)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.4200. Min Act: -0.1700
Data Index: 483999 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.4200. Min Act: -0.1700
Data Index: 350481 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.4200. Min Act: -0.1699
Data Index: 1654528 (Python Code)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.4200. Min Act: -0.1700
Data Index: 454306 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.4037. Min Act: -0.1700
Data Index: 1220818 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.4037. Min Act: -0.1700
Data Index: 953470 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.3874. Min Act: -0.1700
Data Index: 490027 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.3710. Min Act: -0.1700
Data Index: 285591 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.3874. Min Act: -0.1700
Data Index: 1364482 (Python Code)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.3874. Min Act: -0.1700
Data Index: 1502512 (Python Code)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.3874. Min Act: -0.1700
Data Index: 1619713 (Python Code)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.3874. Min Act: -0.1700
Data Index: 410853 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.3710. Min Act: -0.1700
Data Index: 467506 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5012. Min Range: -2.5012
Max Act: 2.3710. Min Act: -0.1700
Data Index: 70863 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19