Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3104 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1207429 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1217726 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0371. Min Act: -0.0002

Data Index: 554993 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1383189 (Python Code)

Max Activating Token Index: 323

Text #4

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0388. Min Act: -0.0002

Data Index: 195464 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0360. Min Act: -0.0003

Data Index: 1591964 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0365. Min Act: -0.0002

Data Index: 126649 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0374. Min Act: -0.0003

Data Index: 1310443 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1343417 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0365. Min Act: -0.0003

Data Index: 1609085 (Python Code)

Max Activating Token Index: 570

Text #10

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1648248 (Python Code)

Max Activating Token Index: 493

Text #11

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0337. Min Act: -0.0003

Data Index: 939697 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0322. Min Act: -0.0002

Data Index: 1309626 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0344. Min Act: -0.0003

Data Index: 673842 (C4 (Web Text))

Max Activating Token Index: 482

Text #14

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0341. Min Act: -0.0003

Data Index: 360191 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0348. Min Act: -0.0002

Data Index: 856251 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0321. Min Act: -0.0003

Data Index: 1400619 (Python Code)

Max Activating Token Index: 766

Text #17

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0327. Min Act: -0.0003

Data Index: 265979 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0363. Min Act: -0.0002

Data Index: 592003 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0341. Min Act: -0.0003

Data Index: 1546520 (Python Code)

Max Activating Token Index: 788