Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1523 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.8221. Min Act: -0.1700
Data Index: 1008404 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.7705. Min Act: -0.1700
Data Index: 760777 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.7446. Min Act: -0.1700
Data Index: 944445 (C4 (Web Text))
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.7446. Min Act: -0.1700
Data Index: 17804 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.7187. Min Act: -0.1700
Data Index: 1046185 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.6927. Min Act: -0.1700
Data Index: 375304 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.6840. Min Act: -0.1700
Data Index: 1186268 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.6840. Min Act: -0.1700
Data Index: 120133 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.6840. Min Act: -0.1700
Data Index: 642005 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.6667. Min Act: -0.1700
Data Index: 715977 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.6493. Min Act: -0.1700
Data Index: 3226 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.6493. Min Act: -0.1700
Data Index: 403248 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.6580. Min Act: -0.1700
Data Index: 735906 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.6580. Min Act: -0.1700
Data Index: 915404 (C4 (Web Text))
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.6493. Min Act: -0.1700
Data Index: 215114 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.6406. Min Act: -0.1700
Data Index: 237474 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.6319. Min Act: -0.1700
Data Index: 623383 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.6319. Min Act: -0.1700
Data Index: 1065133 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.6319. Min Act: -0.1700
Data Index: 939290 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8221. Min Range: -1.8221
Max Act: 1.6406. Min Act: -0.1700
Data Index: 795520 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19