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

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

Neuron 606 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: 1.6301. Min Range: -1.6301

Max Act: 1.6301. Min Act: -0.0001

Data Index: 285503 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.6252. Min Act: -0.0001

Data Index: 804644 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5623. Min Act: -0.0001

Data Index: 581516 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.6059. Min Act: -0.0001

Data Index: 367108 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5712. Min Act: -0.0001

Data Index: 1030626 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5069. Min Act: -0.0001

Data Index: 368546 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.4643. Min Act: -0.0001

Data Index: 1171422 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.5408. Min Act: -0.0001

Data Index: 275197 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.4327. Min Act: -0.0001

Data Index: 184589 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.4628. Min Act: -0.0001

Data Index: 664071 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.3986. Min Act: -0.0001

Data Index: 245814 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.4807. Min Act: -0.0001

Data Index: 232444 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.4582. Min Act: -0.0001

Data Index: 759587 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.4434. Min Act: -0.0001

Data Index: 49588 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.4115. Min Act: -0.0001

Data Index: 1036301 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.3614. Min Act: -0.0001

Data Index: 695584 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.3083. Min Act: -0.0001

Data Index: 690037 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.2861. Min Act: -0.0001

Data Index: 1358413 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.3588. Min Act: -0.0001

Data Index: 864332 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 1.6301. Min Range: -1.6301

Max Act: 1.3621. Min Act: -0.0001

Data Index: 11764 (C4 (Web Text))

Max Activating Token Index: 236