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

Dataset: The Pile

Neuron 3193 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.8192. Min Act: -0.0000

Data Index: 1478803 (The Pile)

Max Activating Token Index: 551

Text #1

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6500. Min Act: -0.0000

Data Index: 426980 (The Pile)

Max Activating Token Index: 249

Text #2

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1871093 (The Pile)

Max Activating Token Index: 543

Text #3

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6099. Min Act: -0.0000

Data Index: 805622 (The Pile)

Max Activating Token Index: 1011

Text #4

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6279. Min Act: -0.0000

Data Index: 1360528 (The Pile)

Max Activating Token Index: 905

Text #5

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5675. Min Act: -0.0000

Data Index: 415224 (The Pile)

Max Activating Token Index: 230

Text #6

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1318463 (The Pile)

Max Activating Token Index: 22

Text #7

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1200413 (The Pile)

Max Activating Token Index: 660

Text #8

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1209889 (The Pile)

Max Activating Token Index: 704

Text #9

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5696. Min Act: -0.0000

Data Index: 1948518 (The Pile)

Max Activating Token Index: 698

Text #10

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1663671 (The Pile)

Max Activating Token Index: 336

Text #11

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1532747 (The Pile)

Max Activating Token Index: 127

Text #12

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5409. Min Act: -0.0000

Data Index: 484939 (The Pile)

Max Activating Token Index: 789

Text #13

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1387043 (The Pile)

Max Activating Token Index: 407

Text #14

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5378. Min Act: -0.0000

Data Index: 169983 (The Pile)

Max Activating Token Index: 935

Text #15

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1393594 (The Pile)

Max Activating Token Index: 394

Text #16

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5257. Min Act: -0.0000

Data Index: 1490831 (The Pile)

Max Activating Token Index: 368

Text #17

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5468. Min Act: -0.0000

Data Index: 556705 (The Pile)

Max Activating Token Index: 515

Text #18

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5251. Min Act: -0.0000

Data Index: 183975 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 0.8192. Min Range: -0.8192

Max Act: 0.5181. Min Act: -0.0000

Data Index: 845562 (The Pile)

Max Activating Token Index: 211