Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 782 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0360. Min Act: -0.0006

Data Index: 858278 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0367. Min Act: -0.0006

Data Index: 957815 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0374. Min Act: -0.0006

Data Index: 1295818 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0354. Min Act: -0.0006

Data Index: 1074304 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0341. Min Act: -0.0006

Data Index: 943349 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0340. Min Act: -0.0006

Data Index: 364140 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0346. Min Act: -0.0006

Data Index: 966559 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0351. Min Act: -0.0006

Data Index: 968343 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0336. Min Act: -0.0006

Data Index: 485247 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0343. Min Act: -0.0006

Data Index: 881542 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0348. Min Act: -0.0006

Data Index: 376927 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0341. Min Act: -0.0006

Data Index: 473405 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0332. Min Act: -0.0006

Data Index: 206265 (C4 (Web Text))

Max Activating Token Index: 322

Text #13

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0340. Min Act: -0.0006

Data Index: 1045996 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0334. Min Act: -0.0006

Data Index: 681439 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0332. Min Act: -0.0006

Data Index: 240056 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0323. Min Act: -0.0006

Data Index: 8905 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0336. Min Act: -0.0006

Data Index: 417379 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0328. Min Act: -0.0006

Data Index: 1204609 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.0374. Min Range: -0.0374

Max Act: 0.0326. Min Act: -0.0006

Data Index: 638111 (C4 (Web Text))

Max Activating Token Index: 988