Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3579 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2280. Min Act: -0.0000

Data Index: 980778 (The Pile)

Max Activating Token Index: 56

Text #1

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2561. Min Act: -0.0000

Data Index: 404223 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.2740. Min Act: -0.0000

Data Index: 899893 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.1290. Min Act: -0.0000

Data Index: 1708092 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0546. Min Act: -0.0000

Data Index: 1732388 (The Pile)

Max Activating Token Index: 993

Text #5

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0407. Min Act: -0.0000

Data Index: 442442 (The Pile)

Max Activating Token Index: 851

Text #6

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.1316. Min Act: -0.0000

Data Index: 685642 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.1433. Min Act: -0.0000

Data Index: 1270850 (The Pile)

Max Activating Token Index: 766

Text #8

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.1028. Min Act: -0.0000

Data Index: 405147 (The Pile)

Max Activating Token Index: 407

Text #9

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0178. Min Act: -0.0000

Data Index: 70636 (The Pile)

Max Activating Token Index: 240

Text #10

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.1461. Min Act: -0.0000

Data Index: 440709 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0752. Min Act: -0.0000

Data Index: 289035 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.1926. Min Act: -0.0000

Data Index: 1539527 (The Pile)

Max Activating Token Index: 478

Text #13

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0970. Min Act: -0.0000

Data Index: 766974 (The Pile)

Max Activating Token Index: 518

Text #14

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0817. Min Act: -0.0000

Data Index: 1416515 (The Pile)

Max Activating Token Index: 723

Text #15

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.3061. Min Act: -0.0000

Data Index: 1818050 (The Pile)

Max Activating Token Index: 666

Text #16

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.1369. Min Act: -0.0000

Data Index: 1334262 (The Pile)

Max Activating Token Index: 622

Text #17

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.1101. Min Act: -0.0000

Data Index: 452033 (The Pile)

Max Activating Token Index: 953

Text #18

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0988. Min Act: -0.0000

Data Index: 860437 (The Pile)

Max Activating Token Index: 559

Text #19

Max Range: 1.3061. Min Range: -1.3061

Max Act: 1.0205. Min Act: -0.0000

Data Index: 800482 (The Pile)

Max Activating Token Index: 349