Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3208 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.6490. Min Act: -0.0001

Data Index: 1204011 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5861. Min Act: -0.0001

Data Index: 571712 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5462. Min Act: -0.0001

Data Index: 758613 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5415. Min Act: -0.0001

Data Index: 774317 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5080. Min Act: -0.0001

Data Index: 48598 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.5166. Min Act: -0.0001

Data Index: 1234554 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4961. Min Act: -0.0001

Data Index: 1205884 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4876. Min Act: -0.0001

Data Index: 671593 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4848. Min Act: -0.0001

Data Index: 1127557 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4585. Min Act: -0.0001

Data Index: 847343 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4579. Min Act: -0.0001

Data Index: 85325 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4248. Min Act: -0.0001

Data Index: 770113 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4534. Min Act: -0.0001

Data Index: 1147721 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4291. Min Act: -0.0001

Data Index: 136014 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4109. Min Act: -0.0001

Data Index: 498334 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4063. Min Act: -0.0001

Data Index: 1107382 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4167. Min Act: -0.0001

Data Index: 1011036 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4155. Min Act: -0.0001

Data Index: 258515 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.4453. Min Act: -0.0001

Data Index: 452663 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.6490. Min Range: -0.6490

Max Act: 0.3638. Min Act: -0.0001

Data Index: 1353313 (C4 (Web Text))

Max Activating Token Index: 644