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

Dataset: The Pile

Neuron 3350 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.4069. Min Act: -0.0000

Data Index: 379295 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3625. Min Act: -0.0000

Data Index: 1672419 (The Pile)

Max Activating Token Index: 472

Text #2

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3211. Min Act: -0.0000

Data Index: 348618 (The Pile)

Max Activating Token Index: 480

Text #3

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3316. Min Act: -0.0000

Data Index: 644158 (The Pile)

Max Activating Token Index: 797

Text #4

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2323. Min Act: -0.0000

Data Index: 139638 (The Pile)

Max Activating Token Index: 822

Text #5

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2307. Min Act: -0.0000

Data Index: 1739450 (The Pile)

Max Activating Token Index: 888

Text #6

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2525. Min Act: -0.0000

Data Index: 223779 (The Pile)

Max Activating Token Index: 466

Text #7

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2583. Min Act: -0.0000

Data Index: 1192815 (The Pile)

Max Activating Token Index: 81

Text #8

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2482. Min Act: -0.0000

Data Index: 496609 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1664566 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2379. Min Act: -0.0000

Data Index: 324987 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2489. Min Act: -0.0000

Data Index: 576546 (The Pile)

Max Activating Token Index: 643

Text #12

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2302. Min Act: -0.0000

Data Index: 563184 (The Pile)

Max Activating Token Index: 757

Text #13

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1234972 (The Pile)

Max Activating Token Index: 237

Text #14

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2194. Min Act: -0.0000

Data Index: 897038 (The Pile)

Max Activating Token Index: 837

Text #15

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1534410 (The Pile)

Max Activating Token Index: 88

Text #16

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1089078 (The Pile)

Max Activating Token Index: 761

Text #17

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2254. Min Act: -0.0000

Data Index: 725473 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2045. Min Act: -0.0000

Data Index: 673844 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2206. Min Act: -0.0000

Data Index: 417564 (The Pile)

Max Activating Token Index: 595