Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2075 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2751. Min Act: -0.0001

Data Index: 14554 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2839. Min Act: -0.0002

Data Index: 604679 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2705. Min Act: -0.0001

Data Index: 542352 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2695. Min Act: -0.0002

Data Index: 159823 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2677. Min Act: -0.0001

Data Index: 1240153 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2393. Min Act: -0.0002

Data Index: 60038 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2407. Min Act: -0.0002

Data Index: 745316 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2552. Min Act: -0.0001

Data Index: 874031 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2576. Min Act: -0.0001

Data Index: 211035 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2401. Min Act: -0.0001

Data Index: 719636 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2254. Min Act: -0.0002

Data Index: 1224180 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2362. Min Act: -0.0001

Data Index: 98308 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2432. Min Act: -0.0001

Data Index: 1026146 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2290. Min Act: -0.0002

Data Index: 635372 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2444. Min Act: -0.0002

Data Index: 1258424 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2262. Min Act: -0.0002

Data Index: 79784 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2259. Min Act: -0.0001

Data Index: 326277 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2406. Min Act: -0.0001

Data Index: 958952 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2276. Min Act: -0.0001

Data Index: 523108 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.2839. Min Range: -0.2839

Max Act: 0.2350. Min Act: -0.0001

Data Index: 637161 (C4 (Web Text))

Max Activating Token Index: 906