Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 258 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.8566. Min Act: -0.1700
Data Index: 237632 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.8566. Min Act: -0.1700
Data Index: 399839 (C4 (Web Text))
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.7770. Min Act: -0.1700
Data Index: 342213 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.7770. Min Act: -0.1700
Data Index: 961435 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.7611. Min Act: -0.1700
Data Index: 582122 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.7611. Min Act: -0.1700
Data Index: 529721 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.7292. Min Act: -0.1700
Data Index: 734893 (C4 (Web Text))
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.7132. Min Act: -0.1700
Data Index: 528810 (C4 (Web Text))
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.7292. Min Act: -0.1700
Data Index: 604019 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.7451. Min Act: -0.1700
Data Index: 1248311 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.7292. Min Act: -0.1700
Data Index: 88246 (C4 (Web Text))
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.7292. Min Act: -0.1700
Data Index: 208917 (C4 (Web Text))
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.7132. Min Act: -0.1700
Data Index: 479819 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.7132. Min Act: -0.1700
Data Index: 1336330 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.6972. Min Act: -0.1700
Data Index: 1569859 (Python Code)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.6972. Min Act: -0.1700
Data Index: 235607 (C4 (Web Text))
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.6972. Min Act: -0.1700
Data Index: 971483 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.6972. Min Act: -0.1700
Data Index: 655139 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.6812. Min Act: -0.1700
Data Index: 1357743 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8566. Min Range: -2.8566
Max Act: 2.6812. Min Act: -0.1700
Data Index: 528358 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #19