Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1559 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.2445. Min Act: -0.0003

Data Index: 345811 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.2345. Min Act: -0.0003

Data Index: 236148 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.2165. Min Act: -0.0003

Data Index: 131410 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.2069. Min Act: -0.0003

Data Index: 770951 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.2220. Min Act: -0.0003

Data Index: 770086 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.2143. Min Act: -0.0003

Data Index: 451640 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.2149. Min Act: -0.0003

Data Index: 1304216 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.2178. Min Act: -0.0003

Data Index: 145532 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.2097. Min Act: -0.0003

Data Index: 6532 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.2049. Min Act: -0.0003

Data Index: 891776 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.2096. Min Act: -0.0003

Data Index: 867899 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.2181. Min Act: -0.0003

Data Index: 1175219 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1981. Min Act: -0.0003

Data Index: 316677 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1964. Min Act: -0.0004

Data Index: 1090760 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.2023. Min Act: -0.0003

Data Index: 648562 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1967. Min Act: -0.0003

Data Index: 866739 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1988. Min Act: -0.0003

Data Index: 1325225 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1757. Min Act: -0.0003

Data Index: 1264647 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1897. Min Act: -0.0004

Data Index: 920504 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.2445. Min Range: -0.2445

Max Act: 0.1812. Min Act: -0.0003

Data Index: 718148 (C4 (Web Text))

Max Activating Token Index: 827