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

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

Neuron 2400 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2959. Min Act: -0.0001

Data Index: 167062 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2101. Min Act: -0.0001

Data Index: 1152175 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2215. Min Act: -0.0001

Data Index: 1102101 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2402. Min Act: -0.0001

Data Index: 1155657 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2173. Min Act: -0.0001

Data Index: 526255 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2155. Min Act: -0.0001

Data Index: 1138321 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2171. Min Act: -0.0002

Data Index: 1252770 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2298. Min Act: -0.0001

Data Index: 1340363 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2268. Min Act: -0.0001

Data Index: 1193752 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2069. Min Act: -0.0001

Data Index: 843089 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2045. Min Act: -0.0001

Data Index: 1265273 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.2087. Min Act: -0.0001

Data Index: 629528 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.1844. Min Act: -0.0001

Data Index: 90718 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.1816. Min Act: -0.0001

Data Index: 64394 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.1968. Min Act: -0.0001

Data Index: 293839 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.1822. Min Act: -0.0001

Data Index: 521908 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.1870. Min Act: -0.0001

Data Index: 5080 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.1882. Min Act: -0.0001

Data Index: 13215 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.1799. Min Act: -0.0001

Data Index: 1290721 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.2959. Min Range: -0.2959

Max Act: 0.1986. Min Act: -0.0001

Data Index: 65702 (C4 (Web Text))

Max Activating Token Index: 9