Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2622 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.5490. Min Act: -0.0001

Data Index: 1304372 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.4950. Min Act: -0.0001

Data Index: 1059639 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.3955. Min Act: -0.0001

Data Index: 955451 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.2615. Min Act: -0.0001

Data Index: 543059 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.4933. Min Act: -0.0001

Data Index: 220812 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.2934. Min Act: -0.0001

Data Index: 940091 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.3144. Min Act: -0.0001

Data Index: 1035448 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.1442. Min Act: -0.0001

Data Index: 64550 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.1680. Min Act: -0.0001

Data Index: 951659 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.2041. Min Act: -0.0001

Data Index: 793918 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.2828. Min Act: -0.0001

Data Index: 779550 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.1197. Min Act: -0.0001

Data Index: 1294402 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 1.5490. Min Range: -1.5490

Max Act: 0.9548. Min Act: -0.0001

Data Index: 929929 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.1021. Min Act: -0.0001

Data Index: 1233319 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.1968. Min Act: -0.0001

Data Index: 399952 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.1654. Min Act: -0.0001

Data Index: 121858 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.1563. Min Act: -0.0001

Data Index: 1259461 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.0789. Min Act: -0.0001

Data Index: 208251 (C4 (Web Text))

Max Activating Token Index: 763

Text #18

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.1462. Min Act: -0.0001

Data Index: 495193 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 1.5490. Min Range: -1.5490

Max Act: 1.1208. Min Act: -0.0001

Data Index: 693364 (C4 (Web Text))

Max Activating Token Index: 67