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

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

Neuron 67 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0480. Min Act: -0.0001

Data Index: 178335 (C4 (Web Text))

Max Activating Token Index: 128

Text #1

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0449. Min Act: -0.0000

Data Index: 1302807 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0436. Min Act: -0.0001

Data Index: 816487 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0383. Min Act: -0.0001

Data Index: 50278 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0406. Min Act: -0.0000

Data Index: 343093 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0399. Min Act: -0.0000

Data Index: 371713 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0411. Min Act: -0.0001

Data Index: 1024109 (C4 (Web Text))

Max Activating Token Index: 711

Text #7

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0371. Min Act: -0.0000

Data Index: 718648 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0380. Min Act: -0.0001

Data Index: 758134 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0352. Min Act: -0.0000

Data Index: 506045 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0289. Min Act: -0.0000

Data Index: 1004838 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0371. Min Act: -0.0000

Data Index: 1540841 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0339. Min Act: -0.0000

Data Index: 1144330 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0308. Min Act: -0.0000

Data Index: 860055 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0338. Min Act: -0.0001

Data Index: 250977 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0309. Min Act: -0.0000

Data Index: 316078 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0338. Min Act: -0.0000

Data Index: 1170723 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0289. Min Act: -0.0000

Data Index: 671043 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0334. Min Act: -0.0000

Data Index: 745368 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.0480. Min Range: -0.0480

Max Act: 0.0333. Min Act: -0.0001

Data Index: 1223525 (C4 (Web Text))

Max Activating Token Index: 75