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

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

Neuron 668 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: 6.7149. Min Range: -6.7149

Max Act: 6.7149. Min Act: -0.0000

Data Index: 917433 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 6.7149. Min Range: -6.7149

Max Act: 4.0861. Min Act: -0.0000

Data Index: 790922 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 6.7149. Min Range: -6.7149

Max Act: 4.2141. Min Act: -0.0000

Data Index: 594109 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 6.7149. Min Range: -6.7149

Max Act: 3.8220. Min Act: -0.0000

Data Index: 1269353 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 6.7149. Min Range: -6.7149

Max Act: 3.8981. Min Act: -0.0000

Data Index: 1534153 (Python Code)

Max Activating Token Index: 700

Text #5

Max Range: 6.7149. Min Range: -6.7149

Max Act: 4.0119. Min Act: -0.0000

Data Index: 171765 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 6.7149. Min Range: -6.7149

Max Act: 3.8407. Min Act: -0.0000

Data Index: 1603220 (Python Code)

Max Activating Token Index: 627

Text #7

Max Range: 6.7149. Min Range: -6.7149

Max Act: 3.8155. Min Act: -0.0000

Data Index: 1404728 (Python Code)

Max Activating Token Index: 1003

Text #8

Max Range: 6.7149. Min Range: -6.7149

Max Act: 3.7229. Min Act: -0.0000

Data Index: 10340 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 6.7149. Min Range: -6.7149

Max Act: 3.6010. Min Act: -0.0000

Data Index: 451264 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 6.7149. Min Range: -6.7149

Max Act: 3.7789. Min Act: -0.0000

Data Index: 298382 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 6.7149. Min Range: -6.7149

Max Act: 3.6019. Min Act: -0.0000

Data Index: 75930 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 6.7149. Min Range: -6.7149

Max Act: 3.2076. Min Act: -0.0000

Data Index: 442498 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 6.7149. Min Range: -6.7149

Max Act: 3.2867. Min Act: -0.0000

Data Index: 997174 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 6.7149. Min Range: -6.7149

Max Act: 3.4110. Min Act: -0.0000

Data Index: 1476705 (Python Code)

Max Activating Token Index: 69

Text #15

Max Range: 6.7149. Min Range: -6.7149

Max Act: 3.2448. Min Act: -0.0000

Data Index: 1344712 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 6.7149. Min Range: -6.7149

Max Act: 3.0647. Min Act: -0.0000

Data Index: 1426842 (Python Code)

Max Activating Token Index: 832

Text #17

Max Range: 6.7149. Min Range: -6.7149

Max Act: 3.3418. Min Act: -0.0000

Data Index: 1589106 (Python Code)

Max Activating Token Index: 688

Text #18

Max Range: 6.7149. Min Range: -6.7149

Max Act: 3.3312. Min Act: -0.0000

Data Index: 1643599 (Python Code)

Max Activating Token Index: 502

Text #19

Max Range: 6.7149. Min Range: -6.7149

Max Act: 3.3036. Min Act: -0.0000

Data Index: 1613655 (Python Code)

Max Activating Token Index: 670