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

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

Neuron 4169 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4112. Min Range: -4.4112

Max Act: 4.1474. Min Act: -0.0000

Data Index: 1643788 (Python Code)

Max Activating Token Index: 988

Text #1

Max Range: 4.4112. Min Range: -4.4112

Max Act: 4.2767. Min Act: -0.0000

Data Index: 1558513 (Python Code)

Max Activating Token Index: 597

Text #2

Max Range: 4.4112. Min Range: -4.4112

Max Act: 4.3199. Min Act: -0.0000

Data Index: 1364804 (Python Code)

Max Activating Token Index: 972

Text #3

Max Range: 4.4112. Min Range: -4.4112

Max Act: 4.1250. Min Act: -0.0000

Data Index: 1593776 (Python Code)

Max Activating Token Index: 674

Text #4

Max Range: 4.4112. Min Range: -4.4112

Max Act: 4.0435. Min Act: -0.0000

Data Index: 1495758 (Python Code)

Max Activating Token Index: 204

Text #5

Max Range: 4.4112. Min Range: -4.4112

Max Act: 4.2586. Min Act: -0.0000

Data Index: 1397749 (Python Code)

Max Activating Token Index: 676

Text #6

Max Range: 4.4112. Min Range: -4.4112

Max Act: 4.4112. Min Act: -0.0000

Data Index: 1565164 (Python Code)

Max Activating Token Index: 977

Text #7

Max Range: 4.4112. Min Range: -4.4112

Max Act: 4.2333. Min Act: -0.0000

Data Index: 1587759 (Python Code)

Max Activating Token Index: 50

Text #8

Max Range: 4.4112. Min Range: -4.4112

Max Act: 4.2258. Min Act: -0.0000

Data Index: 1406347 (Python Code)

Max Activating Token Index: 701

Text #9

Max Range: 4.4112. Min Range: -4.4112

Max Act: 3.8147. Min Act: -0.0000

Data Index: 1551333 (Python Code)

Max Activating Token Index: 704

Text #10

Max Range: 4.4112. Min Range: -4.4112

Max Act: 4.1360. Min Act: -0.0000

Data Index: 1497611 (Python Code)

Max Activating Token Index: 362

Text #11

Max Range: 4.4112. Min Range: -4.4112

Max Act: 4.1702. Min Act: -0.0000

Data Index: 1559592 (Python Code)

Max Activating Token Index: 91

Text #12

Max Range: 4.4112. Min Range: -4.4112

Max Act: 4.0820. Min Act: -0.0000

Data Index: 1471744 (Python Code)

Max Activating Token Index: 706

Text #13

Max Range: 4.4112. Min Range: -4.4112

Max Act: 3.9638. Min Act: -0.0000

Data Index: 1549788 (Python Code)

Max Activating Token Index: 408

Text #14

Max Range: 4.4112. Min Range: -4.4112

Max Act: 4.2878. Min Act: -0.0000

Data Index: 1577845 (Python Code)

Max Activating Token Index: 842

Text #15

Max Range: 4.4112. Min Range: -4.4112

Max Act: 3.8652. Min Act: -0.0000

Data Index: 1586546 (Python Code)

Max Activating Token Index: 144

Text #16

Max Range: 4.4112. Min Range: -4.4112

Max Act: 4.1392. Min Act: -0.0000

Data Index: 1520613 (Python Code)

Max Activating Token Index: 604

Text #17

Max Range: 4.4112. Min Range: -4.4112

Max Act: 3.9363. Min Act: -0.0000

Data Index: 1616623 (Python Code)

Max Activating Token Index: 160

Text #18

Max Range: 4.4112. Min Range: -4.4112

Max Act: 4.1113. Min Act: -0.0000

Data Index: 1413416 (Python Code)

Max Activating Token Index: 1020

Text #19

Max Range: 4.4112. Min Range: -4.4112

Max Act: 3.8569. Min Act: -0.0000

Data Index: 1489204 (Python Code)

Max Activating Token Index: 735