Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1554 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1560. Min Range: -1.1560

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1141713 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 1.1560. Min Range: -1.1560

Max Act: 1.0589. Min Act: -0.0000

Data Index: 694743 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 1.1560. Min Range: -1.1560

Max Act: 1.0933. Min Act: -0.0000

Data Index: 398029 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8963. Min Act: -0.0000

Data Index: 1005276 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8825. Min Act: -0.0000

Data Index: 289322 (C4 (Web Text))

Max Activating Token Index: 918

Text #5

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8507. Min Act: -0.0000

Data Index: 507260 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8774. Min Act: -0.0000

Data Index: 253991 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8162. Min Act: -0.0000

Data Index: 668590 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.8418. Min Act: -0.0000

Data Index: 920186 (C4 (Web Text))

Max Activating Token Index: 981

Text #9

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.7899. Min Act: -0.0000

Data Index: 700333 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.7716. Min Act: -0.0000

Data Index: 16899 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.7652. Min Act: -0.0000

Data Index: 71988 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.7387. Min Act: -0.0000

Data Index: 1000415 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.7649. Min Act: -0.0000

Data Index: 36310 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.7260. Min Act: -0.0000

Data Index: 362994 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1129054 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.7425. Min Act: -0.0000

Data Index: 223834 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.6965. Min Act: -0.0000

Data Index: 1313771 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.7018. Min Act: -0.0000

Data Index: 1248531 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 1.1560. Min Range: -1.1560

Max Act: 0.6356. Min Act: -0.0000

Data Index: 305661 (C4 (Web Text))

Max Activating Token Index: 812