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

Dataset: The Pile

Neuron 2954 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: 0.4575. Min Range: -0.4575

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1993466 (The Pile)

Max Activating Token Index: 456

Text #1

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3960. Min Act: -0.0000

Data Index: 425928 (The Pile)

Max Activating Token Index: 924

Text #2

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.4061. Min Act: -0.0000

Data Index: 1240653 (The Pile)

Max Activating Token Index: 758

Text #3

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1965134 (The Pile)

Max Activating Token Index: 977

Text #4

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3899. Min Act: -0.0000

Data Index: 770809 (The Pile)

Max Activating Token Index: 894

Text #5

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3881. Min Act: -0.0000

Data Index: 645076 (The Pile)

Max Activating Token Index: 812

Text #6

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.4009. Min Act: -0.0000

Data Index: 865622 (The Pile)

Max Activating Token Index: 567

Text #7

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3359. Min Act: -0.0000

Data Index: 91138 (The Pile)

Max Activating Token Index: 495

Text #8

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3689. Min Act: -0.0000

Data Index: 1726616 (The Pile)

Max Activating Token Index: 468

Text #9

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1675319 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3239. Min Act: -0.0000

Data Index: 673389 (The Pile)

Max Activating Token Index: 720

Text #11

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1731245 (The Pile)

Max Activating Token Index: 966

Text #12

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3191. Min Act: -0.0000

Data Index: 482493 (The Pile)

Max Activating Token Index: 484

Text #13

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3344. Min Act: -0.0000

Data Index: 737364 (The Pile)

Max Activating Token Index: 639

Text #14

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3347. Min Act: -0.0000

Data Index: 1643302 (The Pile)

Max Activating Token Index: 937

Text #15

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1411360 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1812739 (The Pile)

Max Activating Token Index: 609

Text #17

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3268. Min Act: -0.0000

Data Index: 948035 (The Pile)

Max Activating Token Index: 190

Text #18

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1591634 (The Pile)

Max Activating Token Index: 911

Text #19

Max Range: 0.4575. Min Range: -0.4575

Max Act: 0.3145. Min Act: -0.0000

Data Index: 194553 (The Pile)

Max Activating Token Index: 96