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

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

Neuron 3695 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: 1.3659. Min Range: -1.3659

Max Act: 1.3659. Min Act: -0.0000

Data Index: 307609 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 1.3659. Min Range: -1.3659

Max Act: 1.0611. Min Act: -0.0000

Data Index: 872797 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.9808. Min Act: -0.0000

Data Index: 517845 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.8913. Min Act: -0.0000

Data Index: 950847 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.9459. Min Act: -0.0000

Data Index: 822823 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.9089. Min Act: -0.0000

Data Index: 1243304 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.9398. Min Act: -0.0000

Data Index: 586692 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.8845. Min Act: -0.0000

Data Index: 443034 (C4 (Web Text))

Max Activating Token Index: 294

Text #8

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.9015. Min Act: -0.0000

Data Index: 298243 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.8305. Min Act: -0.0000

Data Index: 829742 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.8181. Min Act: -0.0000

Data Index: 973534 (C4 (Web Text))

Max Activating Token Index: 991

Text #11

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.8612. Min Act: -0.0000

Data Index: 300170 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.8557. Min Act: -0.0000

Data Index: 201528 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.8546. Min Act: -0.0000

Data Index: 503354 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.7874. Min Act: -0.0000

Data Index: 386465 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.8540. Min Act: -0.0000

Data Index: 258750 (C4 (Web Text))

Max Activating Token Index: 969

Text #16

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.7948. Min Act: -0.0001

Data Index: 204251 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.8030. Min Act: -0.0000

Data Index: 600668 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.7945. Min Act: -0.0000

Data Index: 965294 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 1.3659. Min Range: -1.3659

Max Act: 0.8085. Min Act: -0.0000

Data Index: 807503 (C4 (Web Text))

Max Activating Token Index: 140