Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1713 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.7646. Min Act: -0.0000

Data Index: 1213581 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.7975. Min Act: -0.0000

Data Index: 326095 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6811. Min Act: 0.0000

Data Index: 1054383 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6817. Min Act: -0.0000

Data Index: 413863 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6482. Min Act: -0.0000

Data Index: 95918 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6202. Min Act: -0.0000

Data Index: 337438 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6186. Min Act: -0.0000

Data Index: 783609 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6189. Min Act: 0.0000

Data Index: 1262676 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6167. Min Act: -0.0000

Data Index: 880257 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6233. Min Act: 0.0000

Data Index: 923708 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.6065. Min Act: -0.0000

Data Index: 603910 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5658. Min Act: 0.0000

Data Index: 460178 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5452. Min Act: -0.0000

Data Index: 351957 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5313. Min Act: -0.0000

Data Index: 180170 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5595. Min Act: -0.0000

Data Index: 67839 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5159. Min Act: -0.0000

Data Index: 178264 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5432. Min Act: -0.0000

Data Index: 511334 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5160. Min Act: 0.0000

Data Index: 894953 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5404. Min Act: 0.0000

Data Index: 504275 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 0.7975. Min Range: -0.7975

Max Act: 0.5236. Min Act: 0.0000

Data Index: 708722 (C4 (Web Text))

Max Activating Token Index: 937