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

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

Neuron 3340 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: 0.5350. Min Range: -0.5350

Max Act: 0.5350. Min Act: -0.0001

Data Index: 731267 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.5061. Min Act: -0.0002

Data Index: 1041384 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4691. Min Act: -0.0002

Data Index: 271073 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4459. Min Act: -0.0001

Data Index: 825166 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4577. Min Act: -0.0002

Data Index: 1178381 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4242. Min Act: -0.0001

Data Index: 408766 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4319. Min Act: -0.0001

Data Index: 1161046 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4529. Min Act: -0.0001

Data Index: 889814 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4461. Min Act: -0.0002

Data Index: 462996 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3966. Min Act: -0.0001

Data Index: 576750 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4503. Min Act: -0.0001

Data Index: 724197 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4374. Min Act: -0.0002

Data Index: 729567 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4092. Min Act: -0.0002

Data Index: 225537 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4316. Min Act: -0.0002

Data Index: 241718 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4282. Min Act: -0.0002

Data Index: 172619 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4310. Min Act: -0.0002

Data Index: 1004904 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.3859. Min Act: -0.0002

Data Index: 99738 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4442. Min Act: -0.0002

Data Index: 1138649 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4153. Min Act: -0.0002

Data Index: 382467 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.5350. Min Range: -0.5350

Max Act: 0.4540. Min Act: -0.0002

Data Index: 449 (C4 (Web Text))

Max Activating Token Index: 195