Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3884 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1475. Min Act: -0.0000

Data Index: 636181 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1241. Min Act: -0.0000

Data Index: 657947 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1220. Min Act: -0.0000

Data Index: 428554 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1105. Min Act: -0.0000

Data Index: 362719 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1180. Min Act: -0.0000

Data Index: 207769 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1148. Min Act: -0.0000

Data Index: 463948 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1209. Min Act: -0.0000

Data Index: 1187160 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1199. Min Act: -0.0000

Data Index: 222171 (C4 (Web Text))

Max Activating Token Index: 848

Text #8

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1158. Min Act: -0.0000

Data Index: 666636 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1080. Min Act: -0.0000

Data Index: 180510 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1083. Min Act: -0.0000

Data Index: 1194260 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1131. Min Act: -0.0000

Data Index: 230793 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1095. Min Act: -0.0000

Data Index: 1353538 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1084. Min Act: -0.0000

Data Index: 838193 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1117. Min Act: -0.0000

Data Index: 346394 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1028. Min Act: -0.0000

Data Index: 748008 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1080. Min Act: -0.0000

Data Index: 1154622 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1037. Min Act: -0.0000

Data Index: 98167 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.1041. Min Act: -0.0000

Data Index: 549180 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.1475. Min Range: -0.1475

Max Act: 0.0974. Min Act: -0.0000

Data Index: 968672 (C4 (Web Text))

Max Activating Token Index: 1006