Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1434 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.5403. Min Act: -0.0000

Data Index: 462397 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1119051 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4332. Min Act: -0.0000

Data Index: 948263 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4561. Min Act: -0.0000

Data Index: 1317585 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.4045. Min Act: -0.0000

Data Index: 630403 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3754. Min Act: -0.0000

Data Index: 100024 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3818. Min Act: -0.0000

Data Index: 9289 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3465. Min Act: -0.0000

Data Index: 106323 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3583. Min Act: -0.0000

Data Index: 358634 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3662. Min Act: -0.0000

Data Index: 237060 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3673. Min Act: -0.0000

Data Index: 989253 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3876. Min Act: -0.0000

Data Index: 885621 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3535. Min Act: -0.0000

Data Index: 560714 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3881. Min Act: -0.0000

Data Index: 526865 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3469. Min Act: -0.0000

Data Index: 465605 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3572. Min Act: -0.0000

Data Index: 487745 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3356. Min Act: -0.0000

Data Index: 55732 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3320. Min Act: -0.0000

Data Index: 415315 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3473. Min Act: -0.0000

Data Index: 994479 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.5403. Min Range: -0.5403

Max Act: 0.3254. Min Act: -0.0000

Data Index: 1218712 (C4 (Web Text))

Max Activating Token Index: 56