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

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

Neuron 5038 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2540. Min Act: -0.0001

Data Index: 145763 (C4 (Web Text))

Max Activating Token Index: 296

Text #1

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1160907 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2259. Min Act: -0.0001

Data Index: 6002 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2459. Min Act: -0.0001

Data Index: 356505 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2051. Min Act: -0.0000

Data Index: 839775 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2136. Min Act: -0.0000

Data Index: 487532 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1296069 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1218808 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2075. Min Act: -0.0001

Data Index: 489263 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1844. Min Act: -0.0001

Data Index: 536089 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1782. Min Act: -0.0001

Data Index: 150368 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1773. Min Act: -0.0000

Data Index: 719767 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1838. Min Act: -0.0000

Data Index: 1033188 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1883. Min Act: -0.0001

Data Index: 773940 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1585. Min Act: -0.0000

Data Index: 326667 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1698. Min Act: -0.0001

Data Index: 725335 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1671. Min Act: -0.0000

Data Index: 412933 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1796. Min Act: -0.0000

Data Index: 39972 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1692. Min Act: -0.0000

Data Index: 489662 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1577. Min Act: -0.0000

Data Index: 680084 (C4 (Web Text))

Max Activating Token Index: 1001