Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1643 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.4524. Min Act: -0.0001

Data Index: 1418443 (Python Code)

Max Activating Token Index: 782

Text #1

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.5839. Min Act: -0.0001

Data Index: 1438315 (Python Code)

Max Activating Token Index: 230

Text #2

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.5911. Min Act: -0.0001

Data Index: 1604108 (Python Code)

Max Activating Token Index: 172

Text #3

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.5928. Min Act: -0.0001

Data Index: 1560857 (Python Code)

Max Activating Token Index: 732

Text #4

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.3770. Min Act: -0.0001

Data Index: 1443788 (Python Code)

Max Activating Token Index: 303

Text #5

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.3624. Min Act: -0.0001

Data Index: 1555589 (Python Code)

Max Activating Token Index: 1013

Text #6

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.4185. Min Act: -0.0001

Data Index: 1585188 (Python Code)

Max Activating Token Index: 996

Text #7

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.4578. Min Act: -0.0001

Data Index: 1588139 (Python Code)

Max Activating Token Index: 253

Text #8

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.3846. Min Act: -0.0001

Data Index: 1489013 (Python Code)

Max Activating Token Index: 1016

Text #9

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.4677. Min Act: -0.0001

Data Index: 1572489 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.2563. Min Act: -0.0001

Data Index: 1408821 (Python Code)

Max Activating Token Index: 666

Text #11

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.2896. Min Act: -0.0001

Data Index: 1437556 (Python Code)

Max Activating Token Index: 544

Text #12

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.3028. Min Act: -0.0001

Data Index: 1582659 (Python Code)

Max Activating Token Index: 966

Text #13

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.3871. Min Act: -0.0001

Data Index: 1604634 (Python Code)

Max Activating Token Index: 126

Text #14

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.2424. Min Act: -0.0001

Data Index: 1362593 (Python Code)

Max Activating Token Index: 941

Text #15

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.4706. Min Act: -0.0001

Data Index: 1472273 (Python Code)

Max Activating Token Index: 1018

Text #16

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.4169. Min Act: -0.0001

Data Index: 1411633 (Python Code)

Max Activating Token Index: 211

Text #17

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.3969. Min Act: -0.0001

Data Index: 1439745 (Python Code)

Max Activating Token Index: 670

Text #18

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.4274. Min Act: -0.0001

Data Index: 1522552 (Python Code)

Max Activating Token Index: 631

Text #19

Max Range: 1.5928. Min Range: -1.5928

Max Act: 1.3897. Min Act: -0.0001

Data Index: 1386759 (Python Code)

Max Activating Token Index: 5