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

Dataset: The Pile

Neuron 3652 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: 0.3969. Min Range: -0.3969

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1625216 (The Pile)

Max Activating Token Index: 575

Text #1

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3709. Min Act: -0.0000

Data Index: 899532 (The Pile)

Max Activating Token Index: 1019

Text #2

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3969. Min Act: -0.0000

Data Index: 1081618 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3706. Min Act: -0.0000

Data Index: 1829571 (The Pile)

Max Activating Token Index: 952

Text #4

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3382. Min Act: -0.0000

Data Index: 848068 (The Pile)

Max Activating Token Index: 605

Text #5

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3402. Min Act: -0.0000

Data Index: 201498 (The Pile)

Max Activating Token Index: 740

Text #6

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3400. Min Act: -0.0000

Data Index: 1582415 (The Pile)

Max Activating Token Index: 258

Text #7

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3262. Min Act: -0.0000

Data Index: 972314 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3123. Min Act: -0.0000

Data Index: 1892709 (The Pile)

Max Activating Token Index: 461

Text #9

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3009. Min Act: -0.0000

Data Index: 54999 (The Pile)

Max Activating Token Index: 860

Text #10

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3185. Min Act: -0.0000

Data Index: 784445 (The Pile)

Max Activating Token Index: 343

Text #11

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3148. Min Act: -0.0000

Data Index: 730110 (The Pile)

Max Activating Token Index: 992

Text #12

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.3129. Min Act: -0.0000

Data Index: 315498 (The Pile)

Max Activating Token Index: 545

Text #13

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2959. Min Act: -0.0000

Data Index: 1343059 (The Pile)

Max Activating Token Index: 638

Text #14

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2513. Min Act: -0.0000

Data Index: 944610 (The Pile)

Max Activating Token Index: 813

Text #15

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1940419 (The Pile)

Max Activating Token Index: 871

Text #16

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2925. Min Act: -0.0000

Data Index: 166143 (The Pile)

Max Activating Token Index: 230

Text #17

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2926. Min Act: -0.0000

Data Index: 1147362 (The Pile)

Max Activating Token Index: 733

Text #18

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1264188 (The Pile)

Max Activating Token Index: 762

Text #19

Max Range: 0.3969. Min Range: -0.3969

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1499375 (The Pile)

Max Activating Token Index: 611