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

Dataset: The Pile

Neuron 3656 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3399. Min Act: -0.0000

Data Index: 87554 (The Pile)

Max Activating Token Index: 748

Text #1

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1429875 (The Pile)

Max Activating Token Index: 539

Text #2

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3288. Min Act: -0.0000

Data Index: 875603 (The Pile)

Max Activating Token Index: 622

Text #3

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3320. Min Act: -0.0000

Data Index: 884626 (The Pile)

Max Activating Token Index: 489

Text #4

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3014. Min Act: -0.0000

Data Index: 740290 (The Pile)

Max Activating Token Index: 231

Text #5

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2890. Min Act: -0.0000

Data Index: 1127567 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2710. Min Act: -0.0000

Data Index: 788255 (The Pile)

Max Activating Token Index: 212

Text #7

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2798. Min Act: -0.0000

Data Index: 1955101 (The Pile)

Max Activating Token Index: 580

Text #8

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2810. Min Act: -0.0000

Data Index: 1478934 (The Pile)

Max Activating Token Index: 969

Text #9

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2712. Min Act: -0.0000

Data Index: 1330449 (The Pile)

Max Activating Token Index: 852

Text #10

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2562. Min Act: -0.0000

Data Index: 1092009 (The Pile)

Max Activating Token Index: 90

Text #11

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2348. Min Act: -0.0000

Data Index: 1143556 (The Pile)

Max Activating Token Index: 464

Text #12

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2397. Min Act: -0.0000

Data Index: 260633 (The Pile)

Max Activating Token Index: 879

Text #13

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2590. Min Act: -0.0000

Data Index: 842602 (The Pile)

Max Activating Token Index: 711

Text #14

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1368698 (The Pile)

Max Activating Token Index: 114

Text #15

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2429. Min Act: -0.0000

Data Index: 5394 (The Pile)

Max Activating Token Index: 555

Text #16

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2265. Min Act: -0.0000

Data Index: 243395 (The Pile)

Max Activating Token Index: 206

Text #17

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2086. Min Act: -0.0000

Data Index: 1118978 (The Pile)

Max Activating Token Index: 1018

Text #18

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2367. Min Act: -0.0000

Data Index: 521695 (The Pile)

Max Activating Token Index: 420

Text #19

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2168. Min Act: -0.0000

Data Index: 466937 (The Pile)

Max Activating Token Index: 210