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

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

Neuron 2882 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.5485. Min Act: -0.0001

Data Index: 1005168 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.5404. Min Act: -0.0001

Data Index: 358941 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.3831. Min Act: -0.0001

Data Index: 1465532 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.4560. Min Act: -0.0001

Data Index: 808867 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.2787. Min Act: -0.0001

Data Index: 1607127 (Python Code)

Max Activating Token Index: 902

Text #5

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.3579. Min Act: -0.0001

Data Index: 450550 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.3469. Min Act: -0.0001

Data Index: 1583665 (Python Code)

Max Activating Token Index: 432

Text #7

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.2657. Min Act: -0.0001

Data Index: 1471960 (Python Code)

Max Activating Token Index: 254

Text #8

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.2581. Min Act: -0.0001

Data Index: 1276673 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.1710. Min Act: -0.0001

Data Index: 993074 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.3547. Min Act: -0.0001

Data Index: 257958 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.1907. Min Act: -0.0001

Data Index: 279011 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.2281. Min Act: -0.0001

Data Index: 1472995 (Python Code)

Max Activating Token Index: 172

Text #13

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.1882. Min Act: -0.0001

Data Index: 170309 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.1594. Min Act: -0.0001

Data Index: 881574 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.1627. Min Act: -0.0001

Data Index: 1621303 (Python Code)

Max Activating Token Index: 26

Text #16

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.1801. Min Act: -0.0001

Data Index: 52677 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.1779. Min Act: -0.0001

Data Index: 379595 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.2695. Min Act: -0.0001

Data Index: 1365470 (Python Code)

Max Activating Token Index: 196

Text #19

Max Range: 1.5485. Min Range: -1.5485

Max Act: 1.1719. Min Act: -0.0001

Data Index: 1087671 (C4 (Web Text))

Max Activating Token Index: 3