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

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

Neuron 231 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2169. Min Act: -0.0001

Data Index: 1361891 (Python Code)

Max Activating Token Index: 710

Text #1

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2352. Min Act: -0.0001

Data Index: 1386352 (Python Code)

Max Activating Token Index: 639

Text #2

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2139. Min Act: -0.0001

Data Index: 1401788 (Python Code)

Max Activating Token Index: 521

Text #3

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1963. Min Act: -0.0001

Data Index: 1572459 (Python Code)

Max Activating Token Index: 713

Text #4

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2081. Min Act: -0.0001

Data Index: 1559581 (Python Code)

Max Activating Token Index: 424

Text #5

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.2190. Min Act: -0.0001

Data Index: 1656374 (Python Code)

Max Activating Token Index: 979

Text #6

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1642. Min Act: -0.0001

Data Index: 1245147 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1902. Min Act: -0.0001

Data Index: 1549358 (Python Code)

Max Activating Token Index: 234

Text #8

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1962. Min Act: -0.0001

Data Index: 1505151 (Python Code)

Max Activating Token Index: 498

Text #9

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1956. Min Act: -0.0002

Data Index: 130370 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1520. Min Act: -0.0001

Data Index: 849659 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1945. Min Act: -0.0001

Data Index: 1465038 (Python Code)

Max Activating Token Index: 193

Text #12

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1763. Min Act: -0.0002

Data Index: 1221877 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1911. Min Act: -0.0001

Data Index: 495689 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1531. Min Act: -0.0002

Data Index: 146212 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1774. Min Act: -0.0002

Data Index: 856442 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1773. Min Act: -0.0001

Data Index: 609319 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1760. Min Act: -0.0002

Data Index: 1002096 (C4 (Web Text))

Max Activating Token Index: 329

Text #18

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1747. Min Act: -0.0001

Data Index: 879440 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.2352. Min Range: -0.2352

Max Act: 0.1615. Min Act: -0.0002

Data Index: 380417 (C4 (Web Text))

Max Activating Token Index: 1016