Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1581 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.4961. Min Range: -3.4961

Max Act: 3.4961. Min Act: -0.0000

Data Index: 1814667 (The Pile)

Max Activating Token Index: 670

Text #1

Max Range: 3.4961. Min Range: -3.4961

Max Act: 3.0805. Min Act: -0.0000

Data Index: 1864577 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 3.4961. Min Range: -3.4961

Max Act: 3.0742. Min Act: -0.0000

Data Index: 558634 (The Pile)

Max Activating Token Index: 266

Text #3

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.4333. Min Act: -0.0000

Data Index: 1391275 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.5555. Min Act: -0.0000

Data Index: 490392 (The Pile)

Max Activating Token Index: 755

Text #5

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.5667. Min Act: -0.0000

Data Index: 3736 (The Pile)

Max Activating Token Index: 763

Text #6

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.9132. Min Act: -0.0000

Data Index: 615492 (The Pile)

Max Activating Token Index: 192

Text #7

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.6559. Min Act: -0.0000

Data Index: 1936724 (The Pile)

Max Activating Token Index: 152

Text #8

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.9309. Min Act: -0.0000

Data Index: 2440 (The Pile)

Max Activating Token Index: 962

Text #9

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.7818. Min Act: -0.0000

Data Index: 403141 (The Pile)

Max Activating Token Index: 956

Text #10

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.7171. Min Act: -0.0000

Data Index: 1547996 (The Pile)

Max Activating Token Index: 925

Text #11

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.2154. Min Act: -0.0000

Data Index: 1601690 (The Pile)

Max Activating Token Index: 703

Text #12

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.9679. Min Act: -0.0000

Data Index: 415115 (The Pile)

Max Activating Token Index: 993

Text #13

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.4680. Min Act: -0.0000

Data Index: 639414 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.5769. Min Act: -0.0000

Data Index: 1227955 (The Pile)

Max Activating Token Index: 692

Text #15

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.3939. Min Act: -0.0000

Data Index: 286257 (The Pile)

Max Activating Token Index: 733

Text #16

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.4272. Min Act: -0.0000

Data Index: 1695039 (The Pile)

Max Activating Token Index: 373

Text #17

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.4023. Min Act: -0.0000

Data Index: 1425246 (The Pile)

Max Activating Token Index: 426

Text #18

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.2697. Min Act: -0.0000

Data Index: 137842 (The Pile)

Max Activating Token Index: 566

Text #19

Max Range: 3.4961. Min Range: -3.4961

Max Act: 2.4705. Min Act: -0.0000

Data Index: 383012 (The Pile)

Max Activating Token Index: 1012