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

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

Neuron 3083 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.3724. Min Act: -0.0000

Data Index: 910166 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.3191. Min Act: -0.0000

Data Index: 1113572 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.3269. Min Act: -0.0000

Data Index: 483954 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.3199. Min Act: -0.0000

Data Index: 1119208 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2859. Min Act: -0.0000

Data Index: 469222 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2969. Min Act: -0.0000

Data Index: 186749 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2454. Min Act: -0.0000

Data Index: 1233493 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1252379 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2272. Min Act: -0.0000

Data Index: 688965 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1143522 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2218. Min Act: -0.0000

Data Index: 220776 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2187. Min Act: -0.0000

Data Index: 49225 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2227. Min Act: -0.0000

Data Index: 1006395 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2093. Min Act: -0.0000

Data Index: 319651 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.1965. Min Act: -0.0000

Data Index: 187069 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2004. Min Act: -0.0000

Data Index: 332534 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1081160 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2042. Min Act: -0.0000

Data Index: 3338 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2120. Min Act: -0.0000

Data Index: 823844 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.3724. Min Range: -0.3724

Max Act: 0.2046. Min Act: -0.0000

Data Index: 927644 (C4 (Web Text))

Max Activating Token Index: 240