Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1735 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5080. Min Act: -0.0001

Data Index: 63804 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5963. Min Act: -0.0001

Data Index: 400158 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5532. Min Act: -0.0001

Data Index: 774897 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5115. Min Act: -0.0001

Data Index: 631489 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4815. Min Act: -0.0001

Data Index: 142940 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5431. Min Act: -0.0002

Data Index: 1080952 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4469. Min Act: -0.0002

Data Index: 543559 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4886. Min Act: -0.0001

Data Index: 361326 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4622. Min Act: -0.0001

Data Index: 658602 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4975. Min Act: -0.0002

Data Index: 1249929 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5216. Min Act: -0.0002

Data Index: 686851 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4364. Min Act: -0.0001

Data Index: 1297270 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4593. Min Act: -0.0002

Data Index: 26553 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4567. Min Act: -0.0002

Data Index: 696297 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4676. Min Act: -0.0002

Data Index: 946286 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4332. Min Act: -0.0001

Data Index: 1077742 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4700. Min Act: -0.0002

Data Index: 1017576 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4208. Min Act: -0.0002

Data Index: 681944 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4672. Min Act: -0.0002

Data Index: 1194819 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4509. Min Act: -0.0001

Data Index: 1004602 (C4 (Web Text))

Max Activating Token Index: 143