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

Dataset: The Pile

Neuron 3325 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: 1.3283. Min Range: -1.3283

Max Act: 1.2336. Min Act: -0.0000

Data Index: 1158802 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 1.3283. Min Range: -1.3283

Max Act: 1.3283. Min Act: -0.0000

Data Index: 72941 (The Pile)

Max Activating Token Index: 383

Text #2

Max Range: 1.3283. Min Range: -1.3283

Max Act: 1.1602. Min Act: -0.0000

Data Index: 1006538 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 1.3283. Min Range: -1.3283

Max Act: 1.0236. Min Act: -0.0000

Data Index: 157891 (The Pile)

Max Activating Token Index: 951

Text #4

Max Range: 1.3283. Min Range: -1.3283

Max Act: 1.0825. Min Act: -0.0000

Data Index: 1920691 (The Pile)

Max Activating Token Index: 770

Text #5

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1034704 (The Pile)

Max Activating Token Index: 569

Text #6

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.8931. Min Act: -0.0000

Data Index: 841925 (The Pile)

Max Activating Token Index: 860

Text #7

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.8104. Min Act: -0.0000

Data Index: 676013 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.8704. Min Act: -0.0000

Data Index: 737120 (The Pile)

Max Activating Token Index: 584

Text #9

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.8486. Min Act: -0.0000

Data Index: 1562210 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.7832. Min Act: -0.0000

Data Index: 83086 (The Pile)

Max Activating Token Index: 552

Text #11

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1617307 (The Pile)

Max Activating Token Index: 495

Text #12

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.8271. Min Act: -0.0000

Data Index: 904649 (The Pile)

Max Activating Token Index: 381

Text #13

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.6583. Min Act: -0.0000

Data Index: 345870 (The Pile)

Max Activating Token Index: 742

Text #14

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1774115 (The Pile)

Max Activating Token Index: 666

Text #15

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1903849 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.7035. Min Act: -0.0000

Data Index: 185446 (The Pile)

Max Activating Token Index: 509

Text #17

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.7195. Min Act: -0.0000

Data Index: 741600 (The Pile)

Max Activating Token Index: 593

Text #18

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1953565 (The Pile)

Max Activating Token Index: 112

Text #19

Max Range: 1.3283. Min Range: -1.3283

Max Act: 0.7092. Min Act: -0.0000

Data Index: 647232 (The Pile)

Max Activating Token Index: 39