Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1125 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.3128. Min Act: -0.0001

Data Index: 292303 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.3965. Min Act: -0.0001

Data Index: 738981 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.3197. Min Act: -0.0001

Data Index: 1342469 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.2825. Min Act: -0.0001

Data Index: 232229 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.3083. Min Act: -0.0001

Data Index: 380721 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.3005. Min Act: -0.0001

Data Index: 1281453 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.2289. Min Act: -0.0001

Data Index: 434266 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.3383. Min Act: -0.0001

Data Index: 1041956 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.1919. Min Act: -0.0001

Data Index: 1342665 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.2213. Min Act: -0.0001

Data Index: 234737 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.2444. Min Act: -0.0001

Data Index: 442894 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.2353. Min Act: -0.0001

Data Index: 368602 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.1873. Min Act: -0.0001

Data Index: 974020 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.2477. Min Act: -0.0001

Data Index: 133275 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.0891. Min Act: -0.0001

Data Index: 416312 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.2121. Min Act: -0.0001

Data Index: 626799 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.1393. Min Act: -0.0001

Data Index: 1050444 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.0693. Min Act: -0.0001

Data Index: 1206217 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.0918. Min Act: -0.0001

Data Index: 231887 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 1.3965. Min Range: -1.3965

Max Act: 1.0901. Min Act: -0.0001

Data Index: 656002 (C4 (Web Text))

Max Activating Token Index: 1017