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

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

Neuron 5432 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1233047 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1331076 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.5041. Min Act: -0.0000

Data Index: 266769 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4799. Min Act: -0.0000

Data Index: 273187 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4437. Min Act: -0.0000

Data Index: 858214 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4040. Min Act: -0.0000

Data Index: 693729 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4530. Min Act: -0.0000

Data Index: 689927 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4156. Min Act: -0.0000

Data Index: 753202 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4346. Min Act: -0.0000

Data Index: 941979 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.3891. Min Act: -0.0000

Data Index: 190937 (C4 (Web Text))

Max Activating Token Index: 670

Text #10

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4426. Min Act: -0.0000

Data Index: 1336523 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4301. Min Act: -0.0000

Data Index: 702149 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.3953. Min Act: -0.0000

Data Index: 728327 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4203. Min Act: -0.0000

Data Index: 585661 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.3276. Min Act: -0.0000

Data Index: 213822 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.3693. Min Act: -0.0000

Data Index: 189623 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1320383 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.3675. Min Act: -0.0000

Data Index: 57021 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.4065. Min Act: -0.0000

Data Index: 163231 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.5985. Min Range: -0.5985

Max Act: 0.3742. Min Act: -0.0000

Data Index: 1136861 (C4 (Web Text))

Max Activating Token Index: 212