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

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

Neuron 2855 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1890. Min Act: -0.0001

Data Index: 996146 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1684. Min Act: -0.0001

Data Index: 1055062 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1657. Min Act: -0.0001

Data Index: 903386 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1425. Min Act: -0.0001

Data Index: 399859 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1332. Min Act: -0.0001

Data Index: 948174 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1248. Min Act: -0.0001

Data Index: 209331 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1175. Min Act: -0.0001

Data Index: 14159 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1286. Min Act: -0.0001

Data Index: 259414 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1173140 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1229638 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1075942 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1342090 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1183. Min Act: -0.0001

Data Index: 1008398 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1081642 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1080014 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1176. Min Act: -0.0001

Data Index: 379069 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1183. Min Act: -0.0001

Data Index: 392990 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1213616 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1157138 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.1890. Min Range: -0.1890

Max Act: 0.1145. Min Act: -0.0001

Data Index: 369719 (C4 (Web Text))

Max Activating Token Index: 546