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

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

Neuron 436 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0485. Min Act: -0.0003

Data Index: 1028256 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1365855 (Python Code)

Max Activating Token Index: 975

Text #2

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0455. Min Act: -0.0003

Data Index: 100315 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0482. Min Act: -0.0002

Data Index: 901230 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0477. Min Act: -0.0003

Data Index: 914336 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0460. Min Act: -0.0003

Data Index: 932628 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1131519 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0450. Min Act: -0.0003

Data Index: 403640 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0463. Min Act: -0.0003

Data Index: 681298 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0460. Min Act: -0.0003

Data Index: 10144 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0439. Min Act: -0.0003

Data Index: 972255 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1041273 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0445. Min Act: -0.0003

Data Index: 125433 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0451. Min Act: -0.0003

Data Index: 685276 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0428. Min Act: -0.0003

Data Index: 780656 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0430. Min Act: -0.0004

Data Index: 358705 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1246290 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0431. Min Act: -0.0003

Data Index: 452502 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1078317 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.0497. Min Range: -0.0497

Max Act: 0.0443. Min Act: -0.0004

Data Index: 1353554 (C4 (Web Text))

Max Activating Token Index: 579