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

Dataset: The Pile

Neuron 623 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: 0.6645. Min Range: -0.6645

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1538974 (The Pile)

Max Activating Token Index: 721

Text #1

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.5032. Min Act: -0.0000

Data Index: 757642 (The Pile)

Max Activating Token Index: 57

Text #2

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4850. Min Act: -0.0000

Data Index: 603385 (The Pile)

Max Activating Token Index: 319

Text #3

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4788. Min Act: -0.0000

Data Index: 117067 (The Pile)

Max Activating Token Index: 432

Text #4

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4791. Min Act: -0.0000

Data Index: 949089 (The Pile)

Max Activating Token Index: 360

Text #5

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4434. Min Act: -0.0000

Data Index: 640058 (The Pile)

Max Activating Token Index: 745

Text #6

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4702. Min Act: -0.0000

Data Index: 787093 (The Pile)

Max Activating Token Index: 718

Text #7

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4565. Min Act: -0.0000

Data Index: 999681 (The Pile)

Max Activating Token Index: 547

Text #8

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1194452 (The Pile)

Max Activating Token Index: 192

Text #9

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1292260 (The Pile)

Max Activating Token Index: 748

Text #10

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4618. Min Act: -0.0000

Data Index: 560153 (The Pile)

Max Activating Token Index: 486

Text #11

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1183925 (The Pile)

Max Activating Token Index: 968

Text #12

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4372. Min Act: -0.0000

Data Index: 952417 (The Pile)

Max Activating Token Index: 157

Text #13

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4382. Min Act: -0.0000

Data Index: 232275 (The Pile)

Max Activating Token Index: 867

Text #14

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4520. Min Act: -0.0000

Data Index: 801544 (The Pile)

Max Activating Token Index: 110

Text #15

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4502. Min Act: -0.0000

Data Index: 433927 (The Pile)

Max Activating Token Index: 266

Text #16

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1014586 (The Pile)

Max Activating Token Index: 632

Text #17

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4481. Min Act: -0.0000

Data Index: 908567 (The Pile)

Max Activating Token Index: 15

Text #18

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1189530 (The Pile)

Max Activating Token Index: 301

Text #19

Max Range: 0.6645. Min Range: -0.6645

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1848135 (The Pile)

Max Activating Token Index: 79