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

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

Neuron 2393 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.6727. Min Act: -0.0000

Data Index: 429773 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.6328. Min Act: -0.0000

Data Index: 981332 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4888. Min Act: -0.0000

Data Index: 278775 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1084087 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5168. Min Act: -0.0000

Data Index: 1468263 (Python Code)

Max Activating Token Index: 872

Text #5

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4939. Min Act: -0.0000

Data Index: 919579 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4751. Min Act: -0.0000

Data Index: 242636 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1416638 (Python Code)

Max Activating Token Index: 864

Text #8

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1038943 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1598261 (Python Code)

Max Activating Token Index: 656

Text #10

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4594. Min Act: -0.0000

Data Index: 1599910 (Python Code)

Max Activating Token Index: 870

Text #11

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4596. Min Act: -0.0000

Data Index: 16586 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1565171 (Python Code)

Max Activating Token Index: 1013

Text #13

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4736. Min Act: -0.0000

Data Index: 244346 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4445. Min Act: -0.0000

Data Index: 1638710 (Python Code)

Max Activating Token Index: 487

Text #15

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4433. Min Act: -0.0000

Data Index: 74130 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1434737 (Python Code)

Max Activating Token Index: 114

Text #17

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4587. Min Act: -0.0000

Data Index: 228158 (C4 (Web Text))

Max Activating Token Index: 547

Text #18

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4271. Min Act: -0.0000

Data Index: 187214 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1488242 (Python Code)

Max Activating Token Index: 966