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

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

Neuron 672 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: 0.0374. Min Range: -0.0374

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1131477 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0374. Min Act: -0.0003

Data Index: 615324 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0338. Min Act: -0.0003

Data Index: 33468 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0300. Min Act: -0.0003

Data Index: 288232 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1054626 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0287. Min Act: -0.0003

Data Index: 238232 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0279. Min Act: -0.0003

Data Index: 266811 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0254. Min Act: -0.0003

Data Index: 1046796 (C4 (Web Text))

Max Activating Token Index: 634

Text #8

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0262. Min Act: -0.0003

Data Index: 783616 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1001805 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1219958 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0266. Min Act: -0.0003

Data Index: 742314 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0252. Min Act: -0.0003

Data Index: 881201 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0269. Min Act: -0.0003

Data Index: 787205 (C4 (Web Text))

Max Activating Token Index: 231

Text #14

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0270. Min Act: -0.0003

Data Index: 403919 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0279. Min Act: -0.0003

Data Index: 549634 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0256. Min Act: -0.0003

Data Index: 865797 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0284. Min Act: -0.0003

Data Index: 888793 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0274. Min Act: -0.0003

Data Index: 824524 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0257. Min Act: -0.0003

Data Index: 514972 (C4 (Web Text))

Max Activating Token Index: 237