Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 416 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.5722. Min Act: -0.1700
Data Index: 933252 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.4159. Min Act: -0.1700
Data Index: 485044 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.4159. Min Act: -0.1700
Data Index: 493547 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.4159. Min Act: -0.1700
Data Index: 114063 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3222. Min Act: -0.1700
Data Index: 889913 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.4159. Min Act: -0.1700
Data Index: 1277700 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3534. Min Act: -0.1700
Data Index: 27223 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3222. Min Act: -0.1700
Data Index: 310868 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3847. Min Act: -0.1700
Data Index: 1235748 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.2284. Min Act: -0.1700
Data Index: 644562 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3534. Min Act: -0.1700
Data Index: 870987 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3534. Min Act: -0.1700
Data Index: 459293 (C4 (Web Text))
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.1972. Min Act: -0.1700
Data Index: 444886 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3222. Min Act: -0.1700
Data Index: 1185229 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3222. Min Act: -0.1700
Data Index: 224387 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3222. Min Act: -0.1700
Data Index: 130078 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.2909. Min Act: -0.1700
Data Index: 648808 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3222. Min Act: -0.1700
Data Index: 39329 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.3222. Min Act: -0.1699
Data Index: 1166749 (C4 (Web Text))
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5722. Min Range: -4.5722
Max Act: 4.2597. Min Act: -0.1699
Data Index: 821682 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19