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

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

Neuron 5294 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0458. Min Act: -0.0001

Data Index: 612183 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1345024 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0388. Min Act: -0.0001

Data Index: 1309980 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0361. Min Act: -0.0001

Data Index: 625496 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0233. Min Act: -0.0001

Data Index: 911781 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0325. Min Act: -0.0001

Data Index: 577293 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0294. Min Act: -0.0001

Data Index: 973447 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0342. Min Act: -0.0001

Data Index: 988739 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0293. Min Act: -0.0001

Data Index: 664415 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0304. Min Act: -0.0001

Data Index: 790069 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0301. Min Act: -0.0001

Data Index: 433026 (C4 (Web Text))

Max Activating Token Index: 828

Text #11

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0313. Min Act: -0.0001

Data Index: 957676 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0335. Min Act: -0.0001

Data Index: 901207 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0312. Min Act: -0.0001

Data Index: 262708 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0296. Min Act: -0.0001

Data Index: 257010 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0302. Min Act: -0.0001

Data Index: 461505 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1312538 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0344. Min Act: -0.0001

Data Index: 684131 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0320. Min Act: -0.0001

Data Index: 584018 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0273. Min Act: -0.0001

Data Index: 790981 (C4 (Web Text))

Max Activating Token Index: 842