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

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

Neuron 5781 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1308. Min Range: -3.1308

Max Act: 3.1308. Min Act: -0.0000

Data Index: 379252 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.9943. Min Act: -0.0000

Data Index: 1039847 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.6357. Min Act: -0.0001

Data Index: 390712 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.8693. Min Act: -0.0001

Data Index: 1178097 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.6186. Min Act: -0.0000

Data Index: 1248320 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.6175. Min Act: -0.0001

Data Index: 461020 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.6152. Min Act: -0.0001

Data Index: 709549 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.4693. Min Act: -0.0001

Data Index: 801566 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.4107. Min Act: -0.0000

Data Index: 624133 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.6711. Min Act: -0.0001

Data Index: 1036412 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.3152. Min Act: -0.0000

Data Index: 347597 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.1338. Min Act: -0.0001

Data Index: 905270 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.6123. Min Act: -0.0000

Data Index: 85530 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.6267. Min Act: -0.0000

Data Index: 967432 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.5042. Min Act: -0.0001

Data Index: 182852 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.2907. Min Act: -0.0001

Data Index: 587217 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.2560. Min Act: -0.0001

Data Index: 653839 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.3836. Min Act: -0.0000

Data Index: 947639 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.3399. Min Act: -0.0000

Data Index: 1102673 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 3.1308. Min Range: -3.1308

Max Act: 2.2883. Min Act: -0.0001

Data Index: 1220548 (C4 (Web Text))

Max Activating Token Index: 64