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

Dataset: The Pile

Neuron 1509 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.4503. Min Act: -0.0000

Data Index: 1699923 (The Pile)

Max Activating Token Index: 711

Text #1

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.4089. Min Act: -0.0000

Data Index: 751460 (The Pile)

Max Activating Token Index: 626

Text #2

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3977. Min Act: -0.0000

Data Index: 1447332 (The Pile)

Max Activating Token Index: 476

Text #3

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3786. Min Act: -0.0000

Data Index: 1222517 (The Pile)

Max Activating Token Index: 125

Text #4

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3726. Min Act: -0.0000

Data Index: 1548086 (The Pile)

Max Activating Token Index: 783

Text #5

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1583769 (The Pile)

Max Activating Token Index: 209

Text #6

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3638. Min Act: -0.0000

Data Index: 24068 (The Pile)

Max Activating Token Index: 225

Text #7

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1598987 (The Pile)

Max Activating Token Index: 435

Text #8

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3578. Min Act: -0.0000

Data Index: 488642 (The Pile)

Max Activating Token Index: 138

Text #9

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1658368 (The Pile)

Max Activating Token Index: 415

Text #10

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1105305 (The Pile)

Max Activating Token Index: 564

Text #11

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1486904 (The Pile)

Max Activating Token Index: 370

Text #12

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3599. Min Act: -0.0000

Data Index: 252585 (The Pile)

Max Activating Token Index: 77

Text #13

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3328. Min Act: -0.0000

Data Index: 387354 (The Pile)

Max Activating Token Index: 971

Text #14

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3427. Min Act: -0.0000

Data Index: 133817 (The Pile)

Max Activating Token Index: 890

Text #15

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3573. Min Act: -0.0000

Data Index: 346837 (The Pile)

Max Activating Token Index: 566

Text #16

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3415. Min Act: -0.0000

Data Index: 784917 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3401. Min Act: -0.0000

Data Index: 1232464 (The Pile)

Max Activating Token Index: 56

Text #18

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3271. Min Act: -0.0000

Data Index: 409348 (The Pile)

Max Activating Token Index: 270

Text #19

Max Range: 0.4503. Min Range: -0.4503

Max Act: 0.3251. Min Act: -0.0000

Data Index: 890875 (The Pile)

Max Activating Token Index: 662