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

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

Neuron 1243 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.8409. Min Act: -0.0001

Data Index: 1278021 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.5993. Min Act: -0.0001

Data Index: 883085 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.5895. Min Act: -0.0001

Data Index: 1184703 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.3181. Min Act: -0.0001

Data Index: 897705 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.4761. Min Act: -0.0001

Data Index: 641597 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.4748. Min Act: -0.0001

Data Index: 405722 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.4378. Min Act: -0.0001

Data Index: 442318 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.5911. Min Act: -0.0001

Data Index: 812118 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.5458. Min Act: -0.0001

Data Index: 149946 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.3641. Min Act: -0.0001

Data Index: 944744 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.5435. Min Act: -0.0001

Data Index: 1317149 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.2238. Min Act: -0.0001

Data Index: 869710 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.1994. Min Act: -0.0001

Data Index: 1319547 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.0071. Min Act: -0.0001

Data Index: 999961 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 5.8409. Min Range: -5.8409

Max Act: 4.9489. Min Act: -0.0001

Data Index: 181615 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.0999. Min Act: -0.0001

Data Index: 952335 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.0756. Min Act: -0.0001

Data Index: 667279 (C4 (Web Text))

Max Activating Token Index: 527

Text #17

Max Range: 5.8409. Min Range: -5.8409

Max Act: 4.8990. Min Act: -0.0001

Data Index: 135426 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 5.8409. Min Range: -5.8409

Max Act: 4.8861. Min Act: -0.0001

Data Index: 607418 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 5.8409. Min Range: -5.8409

Max Act: 5.0725. Min Act: -0.0001

Data Index: 330729 (C4 (Web Text))

Max Activating Token Index: 27