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

Dataset: The Pile

Neuron 2389 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6788. Min Act: -0.0000

Data Index: 750235 (The Pile)

Max Activating Token Index: 271

Text #1

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1438007 (The Pile)

Max Activating Token Index: 194

Text #2

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6348. Min Act: -0.0000

Data Index: 136045 (The Pile)

Max Activating Token Index: 672

Text #3

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5990. Min Act: -0.0000

Data Index: 914400 (The Pile)

Max Activating Token Index: 866

Text #4

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6159. Min Act: -0.0000

Data Index: 447095 (The Pile)

Max Activating Token Index: 858

Text #5

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5959. Min Act: -0.0000

Data Index: 571526 (The Pile)

Max Activating Token Index: 409

Text #6

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5923. Min Act: -0.0000

Data Index: 1705743 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5792. Min Act: -0.0000

Data Index: 326921 (The Pile)

Max Activating Token Index: 744

Text #8

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5738. Min Act: -0.0000

Data Index: 1415371 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5668. Min Act: 0.0000

Data Index: 1407338 (The Pile)

Max Activating Token Index: 91

Text #10

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5609. Min Act: -0.0000

Data Index: 543237 (The Pile)

Max Activating Token Index: 351

Text #11

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5805. Min Act: -0.0000

Data Index: 1414823 (The Pile)

Max Activating Token Index: 879

Text #12

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5340. Min Act: -0.0000

Data Index: 80462 (The Pile)

Max Activating Token Index: 317

Text #13

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5506. Min Act: -0.0000

Data Index: 155762 (The Pile)

Max Activating Token Index: 232

Text #14

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6008. Min Act: -0.0000

Data Index: 707140 (The Pile)

Max Activating Token Index: 279

Text #15

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5736. Min Act: 0.0000

Data Index: 1900981 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5379. Min Act: 0.0000

Data Index: 1962092 (The Pile)

Max Activating Token Index: 500

Text #17

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5529. Min Act: -0.0000

Data Index: 632231 (The Pile)

Max Activating Token Index: 555

Text #18

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1608953 (The Pile)

Max Activating Token Index: 52

Text #19

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5133. Min Act: -0.0000

Data Index: 433022 (The Pile)

Max Activating Token Index: 545