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

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

Neuron 1153 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.8243. Min Act: -0.0000

Data Index: 891274 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6928. Min Act: -0.0000

Data Index: 150848 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.7855. Min Act: -0.0000

Data Index: 509887 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.8207. Min Act: -0.0000

Data Index: 258614 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6730. Min Act: -0.0000

Data Index: 97642 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.5568. Min Act: -0.0000

Data Index: 1139086 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6581. Min Act: -0.0000

Data Index: 390296 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6356. Min Act: -0.0000

Data Index: 883577 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.6026. Min Act: -0.0000

Data Index: 231399 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.5400. Min Act: -0.0000

Data Index: 122049 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.4932. Min Act: -0.0000

Data Index: 947734 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.4290. Min Act: -0.0000

Data Index: 1113632 (C4 (Web Text))

Max Activating Token Index: 824

Text #12

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.5164. Min Act: -0.0000

Data Index: 780942 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.3938. Min Act: -0.0000

Data Index: 21097 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.4933. Min Act: -0.0000

Data Index: 716317 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.4871. Min Act: -0.0000

Data Index: 305154 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.4782. Min Act: -0.0000

Data Index: 501250 (C4 (Web Text))

Max Activating Token Index: 313

Text #17

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.4758. Min Act: -0.0000

Data Index: 916308 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.4323. Min Act: -0.0000

Data Index: 1040971 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 1.8243. Min Range: -1.8243

Max Act: 1.3761. Min Act: -0.0000

Data Index: 241692 (C4 (Web Text))

Max Activating Token Index: 805