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

Dataset: The Pile

Neuron 3223 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.5261. Min Act: -0.0000

Data Index: 139123 (The Pile)

Max Activating Token Index: 559

Text #1

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.4584. Min Act: -0.0000

Data Index: 37980 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.0991. Min Act: -0.0000

Data Index: 1636601 (The Pile)

Max Activating Token Index: 1022

Text #3

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.3433. Min Act: -0.0000

Data Index: 1624263 (The Pile)

Max Activating Token Index: 179

Text #4

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.2841. Min Act: -0.0000

Data Index: 842409 (The Pile)

Max Activating Token Index: 1003

Text #5

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.4113. Min Act: -0.0000

Data Index: 1872851 (The Pile)

Max Activating Token Index: 283

Text #6

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.2715. Min Act: -0.0000

Data Index: 615252 (The Pile)

Max Activating Token Index: 582

Text #7

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.0818. Min Act: -0.0000

Data Index: 897037 (The Pile)

Max Activating Token Index: 1009

Text #8

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.1820. Min Act: -0.0000

Data Index: 271199 (The Pile)

Max Activating Token Index: 82

Text #9

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.0466. Min Act: -0.0000

Data Index: 569583 (The Pile)

Max Activating Token Index: 299

Text #10

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.1436. Min Act: -0.0000

Data Index: 731764 (The Pile)

Max Activating Token Index: 781

Text #11

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.1677. Min Act: -0.0000

Data Index: 345997 (The Pile)

Max Activating Token Index: 871

Text #12

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.1474. Min Act: -0.0000

Data Index: 1191473 (The Pile)

Max Activating Token Index: 478

Text #13

Max Range: 3.5261. Min Range: -3.5261

Max Act: 2.9520. Min Act: -0.0000

Data Index: 851463 (The Pile)

Max Activating Token Index: 946

Text #14

Max Range: 3.5261. Min Range: -3.5261

Max Act: 2.6311. Min Act: -0.0000

Data Index: 960764 (The Pile)

Max Activating Token Index: 639

Text #15

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.0606. Min Act: -0.0000

Data Index: 665034 (The Pile)

Max Activating Token Index: 362

Text #16

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.0372. Min Act: -0.0000

Data Index: 998776 (The Pile)

Max Activating Token Index: 791

Text #17

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.0374. Min Act: -0.0000

Data Index: 1632299 (The Pile)

Max Activating Token Index: 442

Text #18

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.1763. Min Act: -0.0000

Data Index: 1154307 (The Pile)

Max Activating Token Index: 570

Text #19

Max Range: 3.5261. Min Range: -3.5261

Max Act: 3.0055. Min Act: -0.0000

Data Index: 264300 (The Pile)

Max Activating Token Index: 859