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

Dataset: The Pile

Neuron 3215 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: 0.6658. Min Range: -0.6658

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1966135 (The Pile)

Max Activating Token Index: 992

Text #1

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.6658. Min Act: -0.0000

Data Index: 745770 (The Pile)

Max Activating Token Index: 540

Text #2

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.4568. Min Act: -0.0000

Data Index: 797665 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1713271 (The Pile)

Max Activating Token Index: 451

Text #4

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.4172. Min Act: -0.0000

Data Index: 996639 (The Pile)

Max Activating Token Index: 513

Text #5

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.4517. Min Act: -0.0000

Data Index: 152195 (The Pile)

Max Activating Token Index: 958

Text #6

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.4106. Min Act: -0.0000

Data Index: 910045 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.4327. Min Act: -0.0000

Data Index: 507540 (The Pile)

Max Activating Token Index: 645

Text #8

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.3913. Min Act: -0.0000

Data Index: 31286 (The Pile)

Max Activating Token Index: 343

Text #9

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.3831. Min Act: -0.0000

Data Index: 978741 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.3953. Min Act: -0.0000

Data Index: 1957277 (The Pile)

Max Activating Token Index: 838

Text #11

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.3917. Min Act: -0.0000

Data Index: 1971820 (The Pile)

Max Activating Token Index: 587

Text #12

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.3464. Min Act: -0.0000

Data Index: 1651232 (The Pile)

Max Activating Token Index: 973

Text #13

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.3681. Min Act: -0.0000

Data Index: 307947 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.2949. Min Act: -0.0000

Data Index: 800794 (The Pile)

Max Activating Token Index: 860

Text #15

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.3200. Min Act: -0.0000

Data Index: 435852 (The Pile)

Max Activating Token Index: 503

Text #16

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.3009. Min Act: -0.0000

Data Index: 536671 (The Pile)

Max Activating Token Index: 568

Text #17

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.2930. Min Act: -0.0000

Data Index: 1701112 (The Pile)

Max Activating Token Index: 619

Text #18

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.2603. Min Act: -0.0000

Data Index: 32936 (The Pile)

Max Activating Token Index: 995

Text #19

Max Range: 0.6658. Min Range: -0.6658

Max Act: 0.3018. Min Act: -0.0000

Data Index: 624076 (The Pile)

Max Activating Token Index: 769