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

Dataset: The Pile

Neuron 3587 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.2446. Min Act: -0.0000

Data Index: 1047548 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.2159. Min Act: -0.0000

Data Index: 1331204 (The Pile)

Max Activating Token Index: 171

Text #2

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0582. Min Act: -0.0000

Data Index: 424409 (The Pile)

Max Activating Token Index: 332

Text #3

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.1770. Min Act: -0.0000

Data Index: 1335414 (The Pile)

Max Activating Token Index: 438

Text #4

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.1605. Min Act: -0.0000

Data Index: 62672 (The Pile)

Max Activating Token Index: 832

Text #5

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.1063. Min Act: -0.0000

Data Index: 586857 (The Pile)

Max Activating Token Index: 913

Text #6

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0764. Min Act: -0.0000

Data Index: 428055 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0878. Min Act: -0.0000

Data Index: 621285 (The Pile)

Max Activating Token Index: 866

Text #8

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0949. Min Act: -0.0000

Data Index: 1237620 (The Pile)

Max Activating Token Index: 825

Text #9

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0433. Min Act: -0.0000

Data Index: 916884 (The Pile)

Max Activating Token Index: 853

Text #10

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0112. Min Act: -0.0000

Data Index: 365303 (The Pile)

Max Activating Token Index: 831

Text #11

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.0461. Min Act: -0.0000

Data Index: 776252 (The Pile)

Max Activating Token Index: 792

Text #12

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9785. Min Act: -0.0000

Data Index: 350607 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 1.2446. Min Range: -1.2446

Max Act: 1.1128. Min Act: -0.0000

Data Index: 248696 (The Pile)

Max Activating Token Index: 740

Text #14

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9502. Min Act: -0.0000

Data Index: 142316 (The Pile)

Max Activating Token Index: 559

Text #15

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1101354 (The Pile)

Max Activating Token Index: 994

Text #16

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9493. Min Act: -0.0000

Data Index: 170471 (The Pile)

Max Activating Token Index: 529

Text #17

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9487. Min Act: -0.0000

Data Index: 1931226 (The Pile)

Max Activating Token Index: 651

Text #18

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.9413. Min Act: -0.0000

Data Index: 1189319 (The Pile)

Max Activating Token Index: 561

Text #19

Max Range: 1.2446. Min Range: -1.2446

Max Act: 0.8660. Min Act: 0.0000

Data Index: 428100 (The Pile)

Max Activating Token Index: 970