Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 235 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.3126. Min Act: -0.0003

Data Index: 464511 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2828. Min Act: -0.0003

Data Index: 779089 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2821. Min Act: -0.0003

Data Index: 1192664 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2623. Min Act: -0.0003

Data Index: 1024835 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2728. Min Act: -0.0003

Data Index: 531203 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2463. Min Act: -0.0003

Data Index: 433477 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2560. Min Act: -0.0003

Data Index: 193550 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2532. Min Act: -0.0003

Data Index: 610024 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2346. Min Act: -0.0003

Data Index: 953801 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2500. Min Act: -0.0003

Data Index: 526978 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2419. Min Act: -0.0003

Data Index: 165391 (C4 (Web Text))

Max Activating Token Index: 643

Text #11

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2573. Min Act: -0.0003

Data Index: 686440 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2521. Min Act: -0.0003

Data Index: 738953 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2407. Min Act: -0.0003

Data Index: 329725 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2415. Min Act: -0.0003

Data Index: 15413 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2304. Min Act: -0.0003

Data Index: 541394 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2542. Min Act: -0.0003

Data Index: 387533 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2370. Min Act: -0.0003

Data Index: 738961 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2383. Min Act: -0.0003

Data Index: 740000 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.3126. Min Range: -0.3126

Max Act: 0.2446. Min Act: -0.0003

Data Index: 1348189 (C4 (Web Text))

Max Activating Token Index: 649