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

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

Neuron 1419 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1131. Min Act: -0.0003

Data Index: 122227 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1250. Min Act: -0.0003

Data Index: 78065 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1340. Min Act: -0.0003

Data Index: 592779 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1129. Min Act: -0.0003

Data Index: 988313 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1312. Min Act: -0.0003

Data Index: 623869 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1254. Min Act: -0.0003

Data Index: 172510 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1183. Min Act: -0.0003

Data Index: 335635 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1092. Min Act: -0.0003

Data Index: 279826 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1142. Min Act: -0.0003

Data Index: 2938 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1090. Min Act: -0.0003

Data Index: 935384 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1135. Min Act: -0.0003

Data Index: 895181 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1093. Min Act: -0.0003

Data Index: 523183 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1044. Min Act: -0.0003

Data Index: 35212 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1161. Min Act: -0.0003

Data Index: 595635 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1079. Min Act: -0.0003

Data Index: 1234560 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1150. Min Act: -0.0003

Data Index: 1284936 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1059. Min Act: -0.0003

Data Index: 528095 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1272. Min Act: -0.0003

Data Index: 266145 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1007. Min Act: -0.0003

Data Index: 1224413 (C4 (Web Text))

Max Activating Token Index: 336

Text #19

Max Range: 0.1340. Min Range: -0.1340

Max Act: 0.1089. Min Act: -0.0003

Data Index: 221843 (C4 (Web Text))

Max Activating Token Index: 121