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

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

Neuron 4701 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: 1.1455. Min Range: -1.1455

Max Act: 1.1408. Min Act: -0.0001

Data Index: 1260298 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 1.1455. Min Range: -1.1455

Max Act: 1.1455. Min Act: -0.0001

Data Index: 1161635 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.9183. Min Act: -0.0000

Data Index: 346345 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8749. Min Act: -0.0000

Data Index: 1264042 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.7608. Min Act: -0.0001

Data Index: 1053628 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8662. Min Act: -0.0000

Data Index: 1162470 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8369. Min Act: -0.0001

Data Index: 1358377 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8859. Min Act: -0.0000

Data Index: 1038669 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8137. Min Act: -0.0001

Data Index: 785586 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8281. Min Act: -0.0001

Data Index: 1110334 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.7770. Min Act: -0.0001

Data Index: 652013 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8302. Min Act: -0.0001

Data Index: 576827 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1162021 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8457. Min Act: -0.0001

Data Index: 802770 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.9003. Min Act: -0.0000

Data Index: 564894 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8068. Min Act: -0.0000

Data Index: 319947 (C4 (Web Text))

Max Activating Token Index: 260

Text #16

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.7865. Min Act: -0.0001

Data Index: 485172 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.8031. Min Act: -0.0001

Data Index: 1029336 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.7475. Min Act: -0.0001

Data Index: 1063491 (C4 (Web Text))

Max Activating Token Index: 936

Text #19

Max Range: 1.1455. Min Range: -1.1455

Max Act: 0.7778. Min Act: -0.0001

Data Index: 169383 (C4 (Web Text))

Max Activating Token Index: 196