Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 54 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.5978. Min Act: -0.1700
Data Index: 645905 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.5656. Min Act: -0.1700
Data Index: 1298250 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.5171. Min Act: -0.1700
Data Index: 251891 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.5010. Min Act: -0.1700
Data Index: 1284637 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.5010. Min Act: -0.1700
Data Index: 1101428 (C4 (Web Text))
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.4847. Min Act: -0.1700
Data Index: 699831 (C4 (Web Text))
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.4523. Min Act: -0.1700
Data Index: 296643 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.4847. Min Act: -0.1700
Data Index: 791458 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.4523. Min Act: -0.1700
Data Index: 654231 (C4 (Web Text))
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.4523. Min Act: -0.1700
Data Index: 880061 (C4 (Web Text))
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.4360. Min Act: -0.1700
Data Index: 503582 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.4197. Min Act: -0.1700
Data Index: 952047 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.4360. Min Act: -0.1700
Data Index: 537869 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.4035. Min Act: -0.1700
Data Index: 1004342 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.4197. Min Act: -0.1700
Data Index: 614251 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.3708. Min Act: -0.1700
Data Index: 151492 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.3708. Min Act: -0.1700
Data Index: 1194220 (C4 (Web Text))
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.3871. Min Act: -0.1700
Data Index: 476730 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.3708. Min Act: -0.1700
Data Index: 1013414 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5978. Min Range: -2.5978
Max Act: 2.3708. Min Act: -0.1700
Data Index: 343049 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #19