Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2017 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.3296. Min Act: -0.1700
Data Index: 696848 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.2671. Min Act: -0.1700
Data Index: 919725 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.2671. Min Act: -0.1700
Data Index: 254103 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.2358. Min Act: -0.1700
Data Index: 642382 (C4 (Web Text))
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.2046. Min Act: -0.1700
Data Index: 275144 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.2046. Min Act: -0.1700
Data Index: 233882 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.1733. Min Act: -0.1700
Data Index: 990307 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.2358. Min Act: -0.1700
Data Index: 337627 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.2046. Min Act: -0.1700
Data Index: 1216945 (C4 (Web Text))
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.2358. Min Act: -0.1700
Data Index: 167808 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.2046. Min Act: -0.1700
Data Index: 1249438 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.1108. Min Act: -0.1700
Data Index: 160265 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.1733. Min Act: -0.1700
Data Index: 318498 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.2046. Min Act: -0.1700
Data Index: 142595 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.1420. Min Act: -0.1700
Data Index: 629216 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.1733. Min Act: -0.1700
Data Index: 270288 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.1733. Min Act: -0.1700
Data Index: 1264047 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.1420. Min Act: -0.1700
Data Index: 99412 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.1420. Min Act: -0.1700
Data Index: 80364 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3296. Min Range: -4.3296
Max Act: 4.1108. Min Act: -0.1700
Data Index: 777787 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19