Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1344 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.3328. Min Act: -0.1700
Data Index: 449237 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.3016. Min Act: -0.1700
Data Index: 238796 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.3016. Min Act: -0.1700
Data Index: 287276 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.2390. Min Act: -0.1700
Data Index: 1164438 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.2078. Min Act: -0.1700
Data Index: 399338 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.2390. Min Act: -0.1700
Data Index: 1007805 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.1453. Min Act: -0.1700
Data Index: 349589 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.1453. Min Act: -0.1700
Data Index: 611882 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.1453. Min Act: -0.1700
Data Index: 1346267 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.2078. Min Act: -0.1700
Data Index: 828426 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.1140. Min Act: -0.1700
Data Index: 1296604 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.1140. Min Act: -0.1700
Data Index: 308626 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.1140. Min Act: -0.1700
Data Index: 1042404 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.0515. Min Act: -0.1700
Data Index: 483444 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.1453. Min Act: -0.1700
Data Index: 500990 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.0515. Min Act: -0.1700
Data Index: 496569 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3328. Min Range: -4.3328
Max Act: 3.9890. Min Act: -0.1700
Data Index: 455281 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3328. Min Range: -4.3328
Max Act: 3.9577. Min Act: -0.1700
Data Index: 228055 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3328. Min Range: -4.3328
Max Act: 3.9890. Min Act: -0.1700
Data Index: 1046905 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3328. Min Range: -4.3328
Max Act: 4.0202. Min Act: -0.1700
Data Index: 65733 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19