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

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

Neuron 5680 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3969. Min Range: -2.3969

Max Act: 2.3969. Min Act: -0.0000

Data Index: 1201883 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 2.3969. Min Range: -2.3969

Max Act: 2.3348. Min Act: -0.0000

Data Index: 1116645 (C4 (Web Text))

Max Activating Token Index: 1013

Text #2

Max Range: 2.3969. Min Range: -2.3969

Max Act: 2.2816. Min Act: -0.0000

Data Index: 8716 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 2.3969. Min Range: -2.3969

Max Act: 2.0893. Min Act: -0.0000

Data Index: 860201 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 2.3969. Min Range: -2.3969

Max Act: 2.0609. Min Act: -0.0000

Data Index: 435578 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 2.3969. Min Range: -2.3969

Max Act: 2.0293. Min Act: -0.0000

Data Index: 403932 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 2.3969. Min Range: -2.3969

Max Act: 2.1260. Min Act: -0.0000

Data Index: 88788 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 2.3969. Min Range: -2.3969

Max Act: 1.9748. Min Act: -0.0000

Data Index: 621723 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 2.3969. Min Range: -2.3969

Max Act: 1.9500. Min Act: -0.0000

Data Index: 1186062 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 2.3969. Min Range: -2.3969

Max Act: 2.0420. Min Act: -0.0000

Data Index: 994156 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 2.3969. Min Range: -2.3969

Max Act: 1.8200. Min Act: -0.0000

Data Index: 72126 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 2.3969. Min Range: -2.3969

Max Act: 1.8906. Min Act: -0.0000

Data Index: 1253857 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 2.3969. Min Range: -2.3969

Max Act: 1.8905. Min Act: -0.0000

Data Index: 761904 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 2.3969. Min Range: -2.3969

Max Act: 1.7348. Min Act: -0.0000

Data Index: 327080 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 2.3969. Min Range: -2.3969

Max Act: 1.9181. Min Act: -0.0000

Data Index: 1286235 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 2.3969. Min Range: -2.3969

Max Act: 1.7993. Min Act: -0.0000

Data Index: 709094 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 2.3969. Min Range: -2.3969

Max Act: 1.7745. Min Act: -0.0000

Data Index: 261874 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 2.3969. Min Range: -2.3969

Max Act: 1.9909. Min Act: -0.0000

Data Index: 1174978 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 2.3969. Min Range: -2.3969

Max Act: 1.6750. Min Act: -0.0000

Data Index: 715535 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 2.3969. Min Range: -2.3969

Max Act: 1.7779. Min Act: -0.0000

Data Index: 375714 (C4 (Web Text))

Max Activating Token Index: 190