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

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

Neuron 370 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: 0.0374. Min Range: -0.0374

Max Act: 0.0374. Min Act: -0.0001

Data Index: 844728 (C4 (Web Text))

Max Activating Token Index: 203

Text #1

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0336. Min Act: -0.0001

Data Index: 744157 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0333. Min Act: -0.0001

Data Index: 6201 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0320. Min Act: -0.0001

Data Index: 1320044 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0348. Min Act: -0.0001

Data Index: 240752 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0323. Min Act: -0.0001

Data Index: 984926 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0322. Min Act: -0.0001

Data Index: 167128 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0330. Min Act: -0.0001

Data Index: 551059 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0308. Min Act: -0.0001

Data Index: 1009211 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0316. Min Act: -0.0001

Data Index: 564782 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0320. Min Act: -0.0001

Data Index: 128428 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0311. Min Act: -0.0001

Data Index: 228854 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0270. Min Act: -0.0001

Data Index: 749709 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1234239 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0311. Min Act: -0.0001

Data Index: 540227 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0297. Min Act: -0.0001

Data Index: 361987 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0322. Min Act: -0.0001

Data Index: 1359722 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0312. Min Act: -0.0001

Data Index: 598764 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0302. Min Act: -0.0001

Data Index: 1329973 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0319. Min Act: -0.0001

Data Index: 91297 (C4 (Web Text))

Max Activating Token Index: 192