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

Dataset: The Pile

Neuron 2329 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.4522. Min Act: -0.0000

Data Index: 207675 (The Pile)

Max Activating Token Index: 443

Text #1

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.4412. Min Act: -0.0000

Data Index: 972111 (The Pile)

Max Activating Token Index: 636

Text #2

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.5547. Min Act: -0.0000

Data Index: 1978098 (The Pile)

Max Activating Token Index: 682

Text #3

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.3172. Min Act: -0.0000

Data Index: 1297619 (The Pile)

Max Activating Token Index: 873

Text #4

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.1915. Min Act: -0.0000

Data Index: 1760608 (The Pile)

Max Activating Token Index: 840

Text #5

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.4730. Min Act: -0.0000

Data Index: 461165 (The Pile)

Max Activating Token Index: 342

Text #6

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.3166. Min Act: -0.0000

Data Index: 1642050 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.3999. Min Act: -0.0000

Data Index: 1397880 (The Pile)

Max Activating Token Index: 612

Text #8

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.3677. Min Act: -0.0000

Data Index: 712307 (The Pile)

Max Activating Token Index: 731

Text #9

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.2510. Min Act: -0.0000

Data Index: 748543 (The Pile)

Max Activating Token Index: 175

Text #10

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.2686. Min Act: -0.0000

Data Index: 751809 (The Pile)

Max Activating Token Index: 83

Text #11

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.0832. Min Act: -0.0000

Data Index: 1110453 (The Pile)

Max Activating Token Index: 971

Text #12

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.2632. Min Act: -0.0000

Data Index: 532834 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.1942. Min Act: -0.0000

Data Index: 1676487 (The Pile)

Max Activating Token Index: 512

Text #14

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.1582. Min Act: -0.0000

Data Index: 1652183 (The Pile)

Max Activating Token Index: 562

Text #15

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.1954. Min Act: -0.0000

Data Index: 1062716 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.1646. Min Act: -0.0000

Data Index: 1461804 (The Pile)

Max Activating Token Index: 664

Text #17

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.2277. Min Act: -0.0000

Data Index: 1617447 (The Pile)

Max Activating Token Index: 419

Text #18

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1006205 (The Pile)

Max Activating Token Index: 25

Text #19

Max Range: 1.5547. Min Range: -1.5547

Max Act: 1.0831. Min Act: -0.0000

Data Index: 926419 (The Pile)

Max Activating Token Index: 160