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

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

Neuron 3883 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.7425. Min Act: -0.0000

Data Index: 1246757 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.4645. Min Act: -0.0000

Data Index: 917487 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.0850. Min Act: -0.0000

Data Index: 548149 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 4.7425. Min Range: -4.7425

Max Act: 3.6456. Min Act: -0.0000

Data Index: 1186990 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.1613. Min Act: -0.0000

Data Index: 700208 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.1226. Min Act: -0.0000

Data Index: 521397 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 4.7425. Min Range: -4.7425

Max Act: 3.7292. Min Act: -0.0000

Data Index: 331413 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 4.7425. Min Range: -4.7425

Max Act: 4.1324. Min Act: -0.0000

Data Index: 981049 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 4.7425. Min Range: -4.7425

Max Act: 3.7368. Min Act: -0.0000

Data Index: 941961 (C4 (Web Text))

Max Activating Token Index: 231

Text #9

Max Range: 4.7425. Min Range: -4.7425

Max Act: 3.4450. Min Act: -0.0000

Data Index: 1196796 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 4.7425. Min Range: -4.7425

Max Act: 3.5584. Min Act: -0.0000

Data Index: 93876 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 4.7425. Min Range: -4.7425

Max Act: 3.5628. Min Act: -0.0000

Data Index: 524609 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 4.7425. Min Range: -4.7425

Max Act: 3.5502. Min Act: -0.0000

Data Index: 849160 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 4.7425. Min Range: -4.7425

Max Act: 3.4651. Min Act: -0.0000

Data Index: 691956 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 4.7425. Min Range: -4.7425

Max Act: 3.5938. Min Act: -0.0000

Data Index: 828483 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 4.7425. Min Range: -4.7425

Max Act: 3.5992. Min Act: -0.0000

Data Index: 525330 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 4.7425. Min Range: -4.7425

Max Act: 3.5680. Min Act: -0.0000

Data Index: 566880 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 4.7425. Min Range: -4.7425

Max Act: 3.7184. Min Act: -0.0000

Data Index: 670105 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 4.7425. Min Range: -4.7425

Max Act: 3.6540. Min Act: -0.0000

Data Index: 193550 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 4.7425. Min Range: -4.7425

Max Act: 3.3256. Min Act: -0.0000

Data Index: 1285002 (C4 (Web Text))

Max Activating Token Index: 94