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

Dataset: The Pile

Neuron 730 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7224. Min Range: -1.7224

Max Act: 1.7224. Min Act: -0.0000

Data Index: 1938596 (The Pile)

Max Activating Token Index: 121

Text #1

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.9225. Min Act: -0.0000

Data Index: 1190019 (The Pile)

Max Activating Token Index: 514

Text #2

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1828629 (The Pile)

Max Activating Token Index: 294

Text #3

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.8339. Min Act: -0.0000

Data Index: 994743 (The Pile)

Max Activating Token Index: 361

Text #4

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1882066 (The Pile)

Max Activating Token Index: 216

Text #5

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.6924. Min Act: -0.0000

Data Index: 429852 (The Pile)

Max Activating Token Index: 240

Text #6

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.7104. Min Act: -0.0000

Data Index: 616258 (The Pile)

Max Activating Token Index: 703

Text #7

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.7660. Min Act: -0.0000

Data Index: 829025 (The Pile)

Max Activating Token Index: 926

Text #8

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.6439. Min Act: -0.0000

Data Index: 780091 (The Pile)

Max Activating Token Index: 730

Text #9

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.7645. Min Act: -0.0000

Data Index: 320799 (The Pile)

Max Activating Token Index: 791

Text #10

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.6803. Min Act: -0.0000

Data Index: 1104568 (The Pile)

Max Activating Token Index: 198

Text #11

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.5577. Min Act: -0.0000

Data Index: 927489 (The Pile)

Max Activating Token Index: 633

Text #12

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.6845. Min Act: -0.0000

Data Index: 1468981 (The Pile)

Max Activating Token Index: 266

Text #13

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.5369. Min Act: -0.0000

Data Index: 800584 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.5495. Min Act: -0.0000

Data Index: 218450 (The Pile)

Max Activating Token Index: 567

Text #15

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1907657 (The Pile)

Max Activating Token Index: 721

Text #16

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.5712. Min Act: -0.0000

Data Index: 226096 (The Pile)

Max Activating Token Index: 564

Text #17

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1471353 (The Pile)

Max Activating Token Index: 247

Text #18

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1409299 (The Pile)

Max Activating Token Index: 374

Text #19

Max Range: 1.7224. Min Range: -1.7224

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1920541 (The Pile)

Max Activating Token Index: 343