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

Dataset: The Pile

Neuron 4254 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: 0.5346. Min Range: -0.5346

Max Act: 0.5297. Min Act: -0.0000

Data Index: 1221482 (The Pile)

Max Activating Token Index: 931

Text #1

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.5346. Min Act: -0.0000

Data Index: 816494 (The Pile)

Max Activating Token Index: 83

Text #2

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4971. Min Act: -0.0000

Data Index: 111571 (The Pile)

Max Activating Token Index: 753

Text #3

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4088. Min Act: -0.0000

Data Index: 801230 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4227. Min Act: -0.0000

Data Index: 76428 (The Pile)

Max Activating Token Index: 228

Text #5

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4130. Min Act: -0.0000

Data Index: 897558 (The Pile)

Max Activating Token Index: 339

Text #6

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3972. Min Act: -0.0000

Data Index: 1338071 (The Pile)

Max Activating Token Index: 838

Text #7

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1774472 (The Pile)

Max Activating Token Index: 893

Text #8

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1070089 (The Pile)

Max Activating Token Index: 527

Text #9

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4146. Min Act: -0.0000

Data Index: 816249 (The Pile)

Max Activating Token Index: 403

Text #10

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3969. Min Act: -0.0000

Data Index: 1865161 (The Pile)

Max Activating Token Index: 735

Text #11

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3951. Min Act: -0.0000

Data Index: 1098080 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4028. Min Act: -0.0000

Data Index: 769382 (The Pile)

Max Activating Token Index: 941

Text #13

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4189. Min Act: -0.0000

Data Index: 399935 (The Pile)

Max Activating Token Index: 664

Text #14

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3884. Min Act: -0.0000

Data Index: 1570552 (The Pile)

Max Activating Token Index: 326

Text #15

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.4007. Min Act: -0.0000

Data Index: 205874 (The Pile)

Max Activating Token Index: 1003

Text #16

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3722. Min Act: -0.0000

Data Index: 50545 (The Pile)

Max Activating Token Index: 402

Text #17

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1848582 (The Pile)

Max Activating Token Index: 284

Text #18

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3858. Min Act: -0.0000

Data Index: 48825 (The Pile)

Max Activating Token Index: 431

Text #19

Max Range: 0.5346. Min Range: -0.5346

Max Act: 0.3686. Min Act: -0.0000

Data Index: 726465 (The Pile)

Max Activating Token Index: 224