Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 207 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.5408. Min Act: -0.0001

Data Index: 552414 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.5365. Min Act: -0.0001

Data Index: 669943 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4837. Min Act: -0.0001

Data Index: 1317204 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4890. Min Act: -0.0001

Data Index: 1074368 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4680. Min Act: -0.0001

Data Index: 134672 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4669. Min Act: -0.0001

Data Index: 871128 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4754. Min Act: -0.0001

Data Index: 353472 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4734. Min Act: -0.0001

Data Index: 382682 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4276. Min Act: -0.0001

Data Index: 758419 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4359. Min Act: -0.0001

Data Index: 290601 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4463. Min Act: -0.0001

Data Index: 350425 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4558. Min Act: -0.0001

Data Index: 536442 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4362. Min Act: -0.0001

Data Index: 1288528 (C4 (Web Text))

Max Activating Token Index: 809

Text #13

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4538. Min Act: -0.0001

Data Index: 196952 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4281. Min Act: -0.0001

Data Index: 870911 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4420. Min Act: -0.0001

Data Index: 365836 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4623. Min Act: -0.0001

Data Index: 319343 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4339. Min Act: -0.0001

Data Index: 1306187 (C4 (Web Text))

Max Activating Token Index: 24

Text #18

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4274. Min Act: -0.0001

Data Index: 1184360 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.5408. Min Range: -0.5408

Max Act: 0.4402. Min Act: -0.0001

Data Index: 1130579 (C4 (Web Text))

Max Activating Token Index: 194