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

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

Neuron 1951 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.3749. Min Act: -0.0002

Data Index: 1402575 (Python Code)

Max Activating Token Index: 268

Text #1

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1382. Min Act: -0.0002

Data Index: 1641598 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.0973. Min Act: -0.0002

Data Index: 1496206 (Python Code)

Max Activating Token Index: 968

Text #3

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1595. Min Act: -0.0002

Data Index: 1435841 (Python Code)

Max Activating Token Index: 153

Text #4

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.2231. Min Act: -0.0002

Data Index: 1572011 (Python Code)

Max Activating Token Index: 405

Text #5

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.2023. Min Act: -0.0002

Data Index: 1400326 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1127. Min Act: -0.0002

Data Index: 1373727 (Python Code)

Max Activating Token Index: 764

Text #7

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1943. Min Act: -0.0002

Data Index: 1554121 (Python Code)

Max Activating Token Index: 284

Text #8

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1668. Min Act: -0.0002

Data Index: 849771 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.0376. Min Act: -0.0002

Data Index: 1463832 (Python Code)

Max Activating Token Index: 297

Text #10

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1258. Min Act: -0.0002

Data Index: 1445764 (Python Code)

Max Activating Token Index: 368

Text #11

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1461. Min Act: -0.0002

Data Index: 1529937 (Python Code)

Max Activating Token Index: 123

Text #12

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1801. Min Act: -0.0002

Data Index: 1569410 (Python Code)

Max Activating Token Index: 111

Text #13

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1847. Min Act: -0.0002

Data Index: 490186 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1018. Min Act: -0.0002

Data Index: 1489690 (Python Code)

Max Activating Token Index: 86

Text #15

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.0196. Min Act: -0.0002

Data Index: 1436953 (Python Code)

Max Activating Token Index: 186

Text #16

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1128. Min Act: -0.0002

Data Index: 1420703 (Python Code)

Max Activating Token Index: 513

Text #17

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.0759. Min Act: -0.0002

Data Index: 1510023 (Python Code)

Max Activating Token Index: 61

Text #18

Max Range: 1.3749. Min Range: -1.3749

Max Act: 1.1380. Min Act: -0.0002

Data Index: 1409347 (Python Code)

Max Activating Token Index: 885

Text #19

Max Range: 1.3749. Min Range: -1.3749

Max Act: 0.9418. Min Act: -0.0002

Data Index: 1556057 (Python Code)

Max Activating Token Index: 125