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

Dataset: The Pile

Neuron 4057 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1852746 (The Pile)

Max Activating Token Index: 21

Text #1

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1205049 (The Pile)

Max Activating Token Index: 733

Text #2

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1791749 (The Pile)

Max Activating Token Index: 410

Text #3

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5979. Min Act: -0.0000

Data Index: 761886 (The Pile)

Max Activating Token Index: 284

Text #4

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6426. Min Act: -0.0000

Data Index: 167425 (The Pile)

Max Activating Token Index: 790

Text #5

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6093. Min Act: -0.0000

Data Index: 362522 (The Pile)

Max Activating Token Index: 476

Text #6

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5900. Min Act: -0.0000

Data Index: 779184 (The Pile)

Max Activating Token Index: 455

Text #7

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6100. Min Act: -0.0000

Data Index: 71785 (The Pile)

Max Activating Token Index: 68

Text #8

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5759. Min Act: -0.0000

Data Index: 251262 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1459570 (The Pile)

Max Activating Token Index: 435

Text #10

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.6351. Min Act: -0.0000

Data Index: 257169 (The Pile)

Max Activating Token Index: 202

Text #11

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5894. Min Act: -0.0000

Data Index: 531110 (The Pile)

Max Activating Token Index: 691

Text #12

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5911. Min Act: -0.0000

Data Index: 294191 (The Pile)

Max Activating Token Index: 613

Text #13

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5065. Min Act: -0.0000

Data Index: 57177 (The Pile)

Max Activating Token Index: 471

Text #14

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.4967. Min Act: -0.0000

Data Index: 493861 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1274703 (The Pile)

Max Activating Token Index: 619

Text #16

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5515. Min Act: -0.0000

Data Index: 1996175 (The Pile)

Max Activating Token Index: 914

Text #17

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5784. Min Act: -0.0000

Data Index: 1108506 (The Pile)

Max Activating Token Index: 1002

Text #18

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1419368 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 0.7388. Min Range: -0.7388

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1173898 (The Pile)

Max Activating Token Index: 663