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

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

Neuron 2578 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2993. Min Act: -0.0001

Data Index: 578341 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2948. Min Act: -0.0001

Data Index: 1098978 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2821. Min Act: -0.0000

Data Index: 968086 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2618. Min Act: -0.0000

Data Index: 458542 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2619. Min Act: -0.0000

Data Index: 230248 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2583. Min Act: -0.0001

Data Index: 325548 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2426. Min Act: 0.0000

Data Index: 48755 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2425. Min Act: 0.0000

Data Index: 740478 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2567. Min Act: 0.0002

Data Index: 879139 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2429. Min Act: -0.0000

Data Index: 86982 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2460. Min Act: -0.0000

Data Index: 168206 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2358. Min Act: -0.0000

Data Index: 244682 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2361. Min Act: -0.0000

Data Index: 240633 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2331. Min Act: 0.0000

Data Index: 541634 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2318. Min Act: -0.0000

Data Index: 525436 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2218. Min Act: -0.0001

Data Index: 157702 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2292. Min Act: -0.0000

Data Index: 1048417 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2390. Min Act: -0.0000

Data Index: 888641 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2153. Min Act: -0.0000

Data Index: 892206 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.2993. Min Range: -0.2993

Max Act: 0.2278. Min Act: -0.0000

Data Index: 1330176 (C4 (Web Text))

Max Activating Token Index: 407