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

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

Neuron 2435 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2955. Min Range: -3.2955

Max Act: 3.2927. Min Act: -0.0000

Data Index: 1612476 (Python Code)

Max Activating Token Index: 504

Text #1

Max Range: 3.2955. Min Range: -3.2955

Max Act: 3.2955. Min Act: -0.0000

Data Index: 1488783 (Python Code)

Max Activating Token Index: 607

Text #2

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.9310. Min Act: -0.0000

Data Index: 1583742 (Python Code)

Max Activating Token Index: 98

Text #3

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.8378. Min Act: -0.0000

Data Index: 1638247 (Python Code)

Max Activating Token Index: 153

Text #4

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.6522. Min Act: -0.0000

Data Index: 1411087 (Python Code)

Max Activating Token Index: 231

Text #5

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.8443. Min Act: -0.0000

Data Index: 1620681 (Python Code)

Max Activating Token Index: 515

Text #6

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.8422. Min Act: -0.0000

Data Index: 1629058 (Python Code)

Max Activating Token Index: 433

Text #7

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.5229. Min Act: -0.0000

Data Index: 1442595 (Python Code)

Max Activating Token Index: 804

Text #8

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.4686. Min Act: -0.0000

Data Index: 1594021 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.4366. Min Act: -0.0000

Data Index: 1478735 (Python Code)

Max Activating Token Index: 125

Text #10

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.2523. Min Act: -0.0000

Data Index: 1521246 (Python Code)

Max Activating Token Index: 893

Text #11

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.2189. Min Act: -0.0000

Data Index: 1615506 (Python Code)

Max Activating Token Index: 200

Text #12

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.1975. Min Act: -0.0000

Data Index: 1500321 (Python Code)

Max Activating Token Index: 705

Text #13

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.1487. Min Act: -0.0000

Data Index: 1460723 (Python Code)

Max Activating Token Index: 515

Text #14

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.1422. Min Act: -0.0000

Data Index: 1431530 (Python Code)

Max Activating Token Index: 178

Text #15

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.2458. Min Act: -0.0000

Data Index: 1478978 (Python Code)

Max Activating Token Index: 434

Text #16

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.2185. Min Act: -0.0000

Data Index: 1466505 (Python Code)

Max Activating Token Index: 109

Text #17

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.0585. Min Act: -0.0000

Data Index: 1621830 (Python Code)

Max Activating Token Index: 595

Text #18

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.0744. Min Act: -0.0000

Data Index: 1567642 (Python Code)

Max Activating Token Index: 51

Text #19

Max Range: 3.2955. Min Range: -3.2955

Max Act: 2.1719. Min Act: -0.0000

Data Index: 1523195 (Python Code)

Max Activating Token Index: 878