Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 484 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.6715. Min Act: -0.1700
Data Index: 887015 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.6394. Min Act: -0.1700
Data Index: 951812 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.6234. Min Act: -0.1700
Data Index: 475165 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.6073. Min Act: -0.1700
Data Index: 1208157 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.6073. Min Act: -0.1700
Data Index: 1005189 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.5751. Min Act: -0.1700
Data Index: 440069 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.5751. Min Act: -0.1700
Data Index: 980029 (C4 (Web Text))
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.5751. Min Act: -0.1700
Data Index: 65199 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.5590. Min Act: -0.1700
Data Index: 488230 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.5428. Min Act: -0.1700
Data Index: 552674 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.5590. Min Act: -0.1700
Data Index: 581734 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.5428. Min Act: -0.1700
Data Index: 586321 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.5428. Min Act: -0.1700
Data Index: 1297524 (C4 (Web Text))
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.5267. Min Act: -0.1700
Data Index: 505113 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.5267. Min Act: -0.1700
Data Index: 753792 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.5105. Min Act: -0.1700
Data Index: 359734 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.5105. Min Act: -0.1700
Data Index: 256190 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.5105. Min Act: -0.1700
Data Index: 1146179 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.5267. Min Act: -0.1700
Data Index: 705006 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6715. Min Range: -2.6715
Max Act: 2.5267. Min Act: -0.1700
Data Index: 258471 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19