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

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

Neuron 4586 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: 0.2767. Min Range: -0.2767

Max Act: 0.2767. Min Act: -0.0001

Data Index: 1457310 (Python Code)

Max Activating Token Index: 253

Text #1

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2571. Min Act: -0.0001

Data Index: 1436136 (Python Code)

Max Activating Token Index: 236

Text #2

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2538. Min Act: -0.0001

Data Index: 1499908 (Python Code)

Max Activating Token Index: 411

Text #3

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2445. Min Act: -0.0001

Data Index: 1460176 (Python Code)

Max Activating Token Index: 766

Text #4

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2404. Min Act: -0.0001

Data Index: 1574406 (Python Code)

Max Activating Token Index: 144

Text #5

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2547. Min Act: -0.0001

Data Index: 1460215 (Python Code)

Max Activating Token Index: 376

Text #6

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2198. Min Act: -0.0001

Data Index: 1557287 (Python Code)

Max Activating Token Index: 221

Text #7

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2455. Min Act: -0.0001

Data Index: 1622020 (Python Code)

Max Activating Token Index: 239

Text #8

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2346. Min Act: -0.0001

Data Index: 1547346 (Python Code)

Max Activating Token Index: 325

Text #9

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2106. Min Act: -0.0001

Data Index: 1474533 (Python Code)

Max Activating Token Index: 605

Text #10

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2236. Min Act: -0.0001

Data Index: 1446549 (Python Code)

Max Activating Token Index: 473

Text #11

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2310. Min Act: -0.0001

Data Index: 1478550 (Python Code)

Max Activating Token Index: 288

Text #12

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2205. Min Act: -0.0001

Data Index: 1443281 (Python Code)

Max Activating Token Index: 251

Text #13

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2261. Min Act: -0.0001

Data Index: 1463073 (Python Code)

Max Activating Token Index: 731

Text #14

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2248. Min Act: -0.0001

Data Index: 1555502 (Python Code)

Max Activating Token Index: 443

Text #15

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2022. Min Act: -0.0001

Data Index: 1374425 (Python Code)

Max Activating Token Index: 236

Text #16

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2001. Min Act: -0.0001

Data Index: 1616436 (Python Code)

Max Activating Token Index: 910

Text #17

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2370. Min Act: -0.0001

Data Index: 1403684 (Python Code)

Max Activating Token Index: 364

Text #18

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2125. Min Act: -0.0001

Data Index: 1626631 (Python Code)

Max Activating Token Index: 61

Text #19

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2114. Min Act: -0.0001

Data Index: 1652603 (Python Code)

Max Activating Token Index: 10