Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4375 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1360. Min Act: -0.0000

Data Index: 1146543 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.1958. Min Act: -0.0000

Data Index: 747154 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.2002. Min Act: -0.0000

Data Index: 231770 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.0747. Min Act: -0.0000

Data Index: 1032693 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.0288. Min Act: -0.0000

Data Index: 1223187 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.0134. Min Act: -0.0000

Data Index: 524281 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.9828. Min Act: -0.0000

Data Index: 664609 (C4 (Web Text))

Max Activating Token Index: 407

Text #7

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.0047. Min Act: -0.0000

Data Index: 612162 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.9689. Min Act: -0.0000

Data Index: 1038476 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.9905. Min Act: -0.0000

Data Index: 184559 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 1.2002. Min Range: -1.2002

Max Act: 1.0204. Min Act: -0.0000

Data Index: 405944 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.9232. Min Act: -0.0000

Data Index: 644396 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.9585. Min Act: -0.0000

Data Index: 462227 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.9837. Min Act: -0.0000

Data Index: 1216164 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.8543. Min Act: -0.0000

Data Index: 729469 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.8552. Min Act: -0.0000

Data Index: 210722 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.8326. Min Act: -0.0000

Data Index: 350715 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.9268. Min Act: -0.0000

Data Index: 12770 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.8529. Min Act: -0.0000

Data Index: 383447 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 1.2002. Min Range: -1.2002

Max Act: 0.8105. Min Act: -0.0000

Data Index: 1198576 (C4 (Web Text))

Max Activating Token Index: 728