Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1893 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.0630. Min Range: -4.0630
Max Act: 4.0317. Min Act: -0.1700
Data Index: 366018 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0630. Min Range: -4.0630
Max Act: 4.0630. Min Act: -0.1700
Data Index: 983554 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0630. Min Range: -4.0630
Max Act: 4.0317. Min Act: -0.1700
Data Index: 1279652 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0630. Min Range: -4.0630
Max Act: 4.0317. Min Act: -0.1700
Data Index: 1295463 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0630. Min Range: -4.0630
Max Act: 3.9692. Min Act: -0.1700
Data Index: 163151 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0630. Min Range: -4.0630
Max Act: 3.9379. Min Act: -0.1700
Data Index: 504281 (C4 (Web Text))
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0630. Min Range: -4.0630
Max Act: 3.9379. Min Act: -0.1700
Data Index: 982760 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0630. Min Range: -4.0630
Max Act: 3.9067. Min Act: -0.1700
Data Index: 586213 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0630. Min Range: -4.0630
Max Act: 3.9379. Min Act: -0.1700
Data Index: 574721 (C4 (Web Text))
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0630. Min Range: -4.0630
Max Act: 3.9379. Min Act: -0.1700
Data Index: 586549 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0630. Min Range: -4.0630
Max Act: 3.9067. Min Act: -0.1700
Data Index: 1348717 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0630. Min Range: -4.0630
Max Act: 3.9067. Min Act: -0.1700
Data Index: 1332557 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0630. Min Range: -4.0630
Max Act: 3.8754. Min Act: -0.1700
Data Index: 342655 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0630. Min Range: -4.0630
Max Act: 3.9067. Min Act: -0.1700
Data Index: 230537 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0630. Min Range: -4.0630
Max Act: 3.8754. Min Act: -0.1700
Data Index: 993137 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0630. Min Range: -4.0630
Max Act: 3.8128. Min Act: -0.1700
Data Index: 748247 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0630. Min Range: -4.0630
Max Act: 3.8754. Min Act: -0.1700
Data Index: 179144 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0630. Min Range: -4.0630
Max Act: 3.8128. Min Act: -0.1700
Data Index: 332099 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0630. Min Range: -4.0630
Max Act: 3.8754. Min Act: -0.1700
Data Index: 51741 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0630. Min Range: -4.0630
Max Act: 3.8441. Min Act: -0.1700
Data Index: 44143 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19