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

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

Neuron 2757 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.3088. Min Act: -0.0001

Data Index: 232521 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.3214. Min Act: -0.0001

Data Index: 204704 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2730. Min Act: -0.0001

Data Index: 626481 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2882. Min Act: -0.0001

Data Index: 552708 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2665. Min Act: -0.0001

Data Index: 629882 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2634. Min Act: -0.0001

Data Index: 452087 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2682. Min Act: -0.0001

Data Index: 1230011 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2592. Min Act: -0.0001

Data Index: 1330022 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2597. Min Act: -0.0001

Data Index: 482460 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2680. Min Act: -0.0001

Data Index: 995336 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2498. Min Act: -0.0001

Data Index: 469827 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2535. Min Act: -0.0001

Data Index: 637703 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2432. Min Act: -0.0001

Data Index: 613651 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2440. Min Act: -0.0001

Data Index: 97516 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2240. Min Act: -0.0001

Data Index: 472762 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2483. Min Act: -0.0001

Data Index: 195369 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2294. Min Act: -0.0001

Data Index: 1192811 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2363. Min Act: -0.0001

Data Index: 301647 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2508. Min Act: -0.0001

Data Index: 1174789 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 0.3214. Min Range: -0.3214

Max Act: 0.2175. Min Act: -0.0001

Data Index: 542835 (C4 (Web Text))

Max Activating Token Index: 230