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

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

Neuron 3067 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.5620. Min Act: -0.0001

Data Index: 1069021 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.5162. Min Act: -0.0001

Data Index: 211446 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.5534. Min Act: -0.0001

Data Index: 1316246 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.5505. Min Act: -0.0001

Data Index: 857064 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4529. Min Act: -0.0001

Data Index: 783504 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4485. Min Act: -0.0002

Data Index: 97381 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4156. Min Act: -0.0001

Data Index: 419087 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4540. Min Act: -0.0001

Data Index: 252194 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4250. Min Act: -0.0001

Data Index: 608662 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4831. Min Act: -0.0001

Data Index: 1047498 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4212. Min Act: -0.0001

Data Index: 476253 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4531. Min Act: -0.0001

Data Index: 261150 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4438. Min Act: -0.0001

Data Index: 1259560 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4157. Min Act: -0.0001

Data Index: 906599 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4477. Min Act: -0.0001

Data Index: 1204067 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4368. Min Act: -0.0002

Data Index: 209594 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4226. Min Act: -0.0001

Data Index: 1150114 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4600. Min Act: -0.0001

Data Index: 1023431 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4544. Min Act: -0.0001

Data Index: 65462 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.5620. Min Range: -0.5620

Max Act: 0.4301. Min Act: -0.0001

Data Index: 1114418 (C4 (Web Text))

Max Activating Token Index: 788