Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1874 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.9236. Min Act: -0.1700
Data Index: 918281 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.8611. Min Act: -0.1700
Data Index: 1163622 (C4 (Web Text))
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.8611. Min Act: -0.1700
Data Index: 1219151 (C4 (Web Text))
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.8611. Min Act: -0.1700
Data Index: 1064367 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.7985. Min Act: -0.1700
Data Index: 1187182 (C4 (Web Text))
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.8611. Min Act: -0.1700
Data Index: 368413 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.7672. Min Act: -0.1700
Data Index: 1349839 (C4 (Web Text))
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.8611. Min Act: -0.1700
Data Index: 1231343 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.8611. Min Act: -0.1700
Data Index: 943515 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.8298. Min Act: -0.1700
Data Index: 405569 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.8298. Min Act: -0.1700
Data Index: 260547 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.7985. Min Act: -0.1700
Data Index: 1258090 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.7985. Min Act: -0.1700
Data Index: 1191308 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.7360. Min Act: -0.1700
Data Index: 934312 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.7672. Min Act: -0.1700
Data Index: 939432 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.7672. Min Act: -0.1700
Data Index: 1059541 (C4 (Web Text))
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.7360. Min Act: -0.1700
Data Index: 1043009 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.7672. Min Act: -0.1700
Data Index: 285171 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.7672. Min Act: -0.1700
Data Index: 1054950 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9236. Min Range: -3.9236
Max Act: 3.7672. Min Act: -0.1700
Data Index: 481402 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19