Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1939 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.8587. Min Act: -0.1700
Data Index: 765641 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.7025. Min Act: -0.1700
Data Index: 1319313 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.6400. Min Act: -0.1700
Data Index: 617493 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.6400. Min Act: -0.1700
Data Index: 1203694 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.5462. Min Act: -0.1700
Data Index: 738815 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.5462. Min Act: -0.1700
Data Index: 772194 (C4 (Web Text))
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.5150. Min Act: -0.1700
Data Index: 126167 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.4212. Min Act: -0.1700
Data Index: 532365 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.5150. Min Act: -0.1700
Data Index: 302194 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.5150. Min Act: -0.1700
Data Index: 423110 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.4212. Min Act: -0.1700
Data Index: 491159 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.3900. Min Act: -0.1700
Data Index: 185295 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.4212. Min Act: -0.1700
Data Index: 569340 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.3900. Min Act: -0.1700
Data Index: 515742 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.3900. Min Act: -0.1700
Data Index: 1341450 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.3587. Min Act: -0.1700
Data Index: 1085500 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.3900. Min Act: -0.1700
Data Index: 1231045 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.3900. Min Act: -0.1700
Data Index: 219301 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.3275. Min Act: -0.1700
Data Index: 592494 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8587. Min Range: -4.8587
Max Act: 4.3275. Min Act: -0.1700
Data Index: 1101483 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19