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

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

Neuron 4068 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0795. Min Act: -0.0002

Data Index: 539730 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0693. Min Act: -0.0002

Data Index: 16220 (C4 (Web Text))

Max Activating Token Index: 513

Text #2

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1166708 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0510. Min Act: -0.0002

Data Index: 475723 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0545. Min Act: -0.0002

Data Index: 828394 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0524. Min Act: -0.0002

Data Index: 23020 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1347726 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1245616 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0505. Min Act: -0.0002

Data Index: 654928 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0489. Min Act: -0.0002

Data Index: 852111 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0483. Min Act: -0.0002

Data Index: 721813 (C4 (Web Text))

Max Activating Token Index: 310

Text #11

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0477. Min Act: -0.0002

Data Index: 311101 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0474. Min Act: -0.0002

Data Index: 275736 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0467. Min Act: -0.0002

Data Index: 341000 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0465. Min Act: -0.0002

Data Index: 164088 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0460. Min Act: -0.0002

Data Index: 24109 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1021956 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0446. Min Act: -0.0002

Data Index: 989945 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0445. Min Act: -0.0002

Data Index: 1158293 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0436. Min Act: -0.0002

Data Index: 530995 (C4 (Web Text))

Max Activating Token Index: 889