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

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

Neuron 2671 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.2473. Min Act: -0.0001

Data Index: 632320 (C4 (Web Text))

Max Activating Token Index: 659

Text #1

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.3411. Min Act: -0.0001

Data Index: 1189511 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 3.3411. Min Range: -3.3411

Max Act: 3.1639. Min Act: -0.0001

Data Index: 227818 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.6026. Min Act: -0.0001

Data Index: 884210 (C4 (Web Text))

Max Activating Token Index: 326

Text #4

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.9724. Min Act: -0.0001

Data Index: 300777 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.7139. Min Act: -0.0001

Data Index: 191450 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.8006. Min Act: -0.0001

Data Index: 253341 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.7807. Min Act: -0.0001

Data Index: 424685 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.7443. Min Act: -0.0001

Data Index: 146195 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.7136. Min Act: -0.0001

Data Index: 117537 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.7705. Min Act: -0.0001

Data Index: 1290774 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.4609. Min Act: -0.0001

Data Index: 628021 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.4291. Min Act: -0.0001

Data Index: 455635 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.4214. Min Act: -0.0001

Data Index: 1265983 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.5382. Min Act: -0.0001

Data Index: 747875 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.4277. Min Act: -0.0001

Data Index: 23280 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.3414. Min Act: -0.0001

Data Index: 719897 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.5027. Min Act: -0.0001

Data Index: 1148138 (C4 (Web Text))

Max Activating Token Index: 437

Text #18

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.2979. Min Act: -0.0001

Data Index: 41234 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 3.3411. Min Range: -3.3411

Max Act: 2.3571. Min Act: -0.0001

Data Index: 1006331 (C4 (Web Text))

Max Activating Token Index: 299