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

Dataset: The Pile

Neuron 3087 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9321. Min Act: -0.0000

Data Index: 982456 (The Pile)

Max Activating Token Index: 595

Text #1

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1808379 (The Pile)

Max Activating Token Index: 318

Text #2

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1068700 (The Pile)

Max Activating Token Index: 188

Text #3

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8994. Min Act: -0.0000

Data Index: 1335035 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8141. Min Act: -0.0000

Data Index: 116809 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8236. Min Act: -0.0000

Data Index: 116949 (The Pile)

Max Activating Token Index: 722

Text #6

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7621. Min Act: -0.0000

Data Index: 844742 (The Pile)

Max Activating Token Index: 37

Text #7

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7935. Min Act: -0.0000

Data Index: 895779 (The Pile)

Max Activating Token Index: 322

Text #8

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7377. Min Act: -0.0000

Data Index: 667605 (The Pile)

Max Activating Token Index: 422

Text #9

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7144. Min Act: -0.0000

Data Index: 552653 (The Pile)

Max Activating Token Index: 120

Text #10

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7574. Min Act: -0.0000

Data Index: 279795 (The Pile)

Max Activating Token Index: 465

Text #11

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7264. Min Act: -0.0000

Data Index: 1371729 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7002. Min Act: -0.0000

Data Index: 568330 (The Pile)

Max Activating Token Index: 309

Text #13

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7005. Min Act: -0.0000

Data Index: 1881529 (The Pile)

Max Activating Token Index: 774

Text #14

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7005. Min Act: -0.0000

Data Index: 1218608 (The Pile)

Max Activating Token Index: 345

Text #15

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.6540. Min Act: -0.0000

Data Index: 47483 (The Pile)

Max Activating Token Index: 271

Text #16

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7114. Min Act: -0.0000

Data Index: 434182 (The Pile)

Max Activating Token Index: 579

Text #17

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1125582 (The Pile)

Max Activating Token Index: 185

Text #18

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7534. Min Act: -0.0000

Data Index: 466709 (The Pile)

Max Activating Token Index: 640

Text #19

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7725. Min Act: -0.0000

Data Index: 595442 (The Pile)

Max Activating Token Index: 885