Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 45 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.5393. Min Act: -0.1700
Data Index: 1134503 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.5232. Min Act: -0.1700
Data Index: 446237 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.5070. Min Act: -0.1700
Data Index: 671467 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.5070. Min Act: -0.1700
Data Index: 884425 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.4584. Min Act: -0.1700
Data Index: 828995 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.4421. Min Act: -0.1700
Data Index: 1161498 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.4258. Min Act: -0.1700
Data Index: 868787 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.4095. Min Act: -0.1700
Data Index: 1088412 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.4095. Min Act: -0.1700
Data Index: 1226766 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.4095. Min Act: -0.1700
Data Index: 1218612 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.3932. Min Act: -0.1700
Data Index: 924206 (C4 (Web Text))
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.3769. Min Act: -0.1700
Data Index: 481212 (C4 (Web Text))
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.3932. Min Act: -0.1700
Data Index: 467789 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.3769. Min Act: -0.1700
Data Index: 445053 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.3769. Min Act: -0.1700
Data Index: 1333979 (C4 (Web Text))
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.3932. Min Act: -0.1700
Data Index: 515825 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.3769. Min Act: -0.1700
Data Index: 662550 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.3605. Min Act: -0.1700
Data Index: 922257 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.3442. Min Act: -0.1700
Data Index: 1354092 (C4 (Web Text))
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5393. Min Range: -2.5393
Max Act: 2.3442. Min Act: -0.1700
Data Index: 14877 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19