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

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

Neuron 143 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3817. Min Range: -5.3817

Max Act: 5.3817. Min Act: -0.0001

Data Index: 297812 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.9669. Min Act: -0.0001

Data Index: 1157948 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.8527. Min Act: -0.0001

Data Index: 942642 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 5.3817. Min Range: -5.3817

Max Act: 3.8751. Min Act: -0.0001

Data Index: 292092 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.5284. Min Act: -0.0001

Data Index: 1348181 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.6602. Min Act: -0.0001

Data Index: 1192830 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.4709. Min Act: -0.0001

Data Index: 620187 (C4 (Web Text))

Max Activating Token Index: 228

Text #7

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.2274. Min Act: -0.0001

Data Index: 1354266 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.3443. Min Act: -0.0001

Data Index: 323949 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.3234. Min Act: -0.0001

Data Index: 931441 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.4897. Min Act: -0.0001

Data Index: 1310459 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.2865. Min Act: -0.0001

Data Index: 829757 (C4 (Web Text))

Max Activating Token Index: 190

Text #12

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.2835. Min Act: -0.0001

Data Index: 1139458 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.1154. Min Act: -0.0001

Data Index: 485662 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.2457. Min Act: -0.0001

Data Index: 1142115 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.2721. Min Act: -0.0001

Data Index: 130184 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.2632. Min Act: -0.0001

Data Index: 455633 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.4361. Min Act: -0.0001

Data Index: 448854 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 5.3817. Min Range: -5.3817

Max Act: 3.8973. Min Act: -0.0001

Data Index: 988312 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 5.3817. Min Range: -5.3817

Max Act: 4.3478. Min Act: -0.0001

Data Index: 694268 (C4 (Web Text))

Max Activating Token Index: 945