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

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

Neuron 2206 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.3178. Min Act: -0.0000

Data Index: 522625 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.3195. Min Act: -0.0001

Data Index: 552051 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2828. Min Act: -0.0000

Data Index: 1346273 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2784. Min Act: -0.0000

Data Index: 900954 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.3139. Min Act: -0.0000

Data Index: 386445 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2548. Min Act: -0.0001

Data Index: 335549 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2612. Min Act: -0.0001

Data Index: 900502 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2935. Min Act: -0.0000

Data Index: 1174358 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2564. Min Act: -0.0000

Data Index: 227695 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2637. Min Act: -0.0000

Data Index: 1187115 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2400. Min Act: -0.0001

Data Index: 375897 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2522. Min Act: -0.0000

Data Index: 901191 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2510. Min Act: -0.0000

Data Index: 315207 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2681. Min Act: -0.0000

Data Index: 412243 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2486. Min Act: -0.0001

Data Index: 323486 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2748. Min Act: -0.0000

Data Index: 815246 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2584. Min Act: -0.0000

Data Index: 83146 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2348. Min Act: -0.0001

Data Index: 487091 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2519. Min Act: -0.0000

Data Index: 570488 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2443. Min Act: -0.0000

Data Index: 627488 (C4 (Web Text))

Max Activating Token Index: 966