Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3868. Min Act: -0.1700
Data Index: 272550 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3705. Min Act: -0.1700
Data Index: 1355855 (C4 (Web Text))
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3705. Min Act: -0.1700
Data Index: 546375 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3705. Min Act: -0.1700
Data Index: 1116471 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3541. Min Act: -0.1700
Data Index: 1183533 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3541. Min Act: -0.1700
Data Index: 131527 (C4 (Web Text))
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3541. Min Act: -0.1700
Data Index: 799742 (C4 (Web Text))
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3541. Min Act: -0.1700
Data Index: 1054598 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3541. Min Act: -0.1700
Data Index: 812659 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3541. Min Act: -0.1700
Data Index: 1123132 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3541. Min Act: -0.1700
Data Index: 647148 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3541. Min Act: -0.1700
Data Index: 822232 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3541. Min Act: -0.1700
Data Index: 51439 (C4 (Web Text))
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3378. Min Act: -0.1700
Data Index: 186887 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3378. Min Act: -0.1700
Data Index: 1063179 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3378. Min Act: -0.1700
Data Index: 286724 (C4 (Web Text))
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3378. Min Act: -0.1700
Data Index: 765493 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3541. Min Act: -0.1700
Data Index: 506267 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3049. Min Act: -0.1700
Data Index: 1035971 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3868. Min Range: -2.3868
Max Act: 2.3378. Min Act: -0.1700
Data Index: 973384 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19