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

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

Neuron 3404 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: 2.7392. Min Range: -2.7392

Max Act: 2.4945. Min Act: -0.0000

Data Index: 858111 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 2.7392. Min Range: -2.7392

Max Act: 2.7392. Min Act: -0.0000

Data Index: 1301563 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 2.7392. Min Range: -2.7392

Max Act: 2.2719. Min Act: -0.0000

Data Index: 910202 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 2.7392. Min Range: -2.7392

Max Act: 2.1285. Min Act: -0.0000

Data Index: 1535668 (Python Code)

Max Activating Token Index: 711

Text #4

Max Range: 2.7392. Min Range: -2.7392

Max Act: 2.2314. Min Act: -0.0000

Data Index: 214729 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 2.7392. Min Range: -2.7392

Max Act: 2.2086. Min Act: -0.0000

Data Index: 202951 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 2.7392. Min Range: -2.7392

Max Act: 2.0655. Min Act: -0.0000

Data Index: 710358 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 2.7392. Min Range: -2.7392

Max Act: 2.1803. Min Act: -0.0000

Data Index: 448756 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 2.7392. Min Range: -2.7392

Max Act: 1.9930. Min Act: -0.0000

Data Index: 1515418 (Python Code)

Max Activating Token Index: 856

Text #9

Max Range: 2.7392. Min Range: -2.7392

Max Act: 1.9892. Min Act: -0.0000

Data Index: 146021 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 2.7392. Min Range: -2.7392

Max Act: 1.9884. Min Act: -0.0000

Data Index: 582974 (C4 (Web Text))

Max Activating Token Index: 44

Text #11

Max Range: 2.7392. Min Range: -2.7392

Max Act: 1.9737. Min Act: -0.0000

Data Index: 1160719 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 2.7392. Min Range: -2.7392

Max Act: 1.9657. Min Act: -0.0000

Data Index: 984330 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 2.7392. Min Range: -2.7392

Max Act: 1.9364. Min Act: -0.0000

Data Index: 889052 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 2.7392. Min Range: -2.7392

Max Act: 1.9370. Min Act: -0.0000

Data Index: 389176 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 2.7392. Min Range: -2.7392

Max Act: 1.4454. Min Act: -0.0000

Data Index: 455064 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 2.7392. Min Range: -2.7392

Max Act: 1.8128. Min Act: -0.0000

Data Index: 144959 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 2.7392. Min Range: -2.7392

Max Act: 1.9066. Min Act: -0.0000

Data Index: 1058912 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 2.7392. Min Range: -2.7392

Max Act: 1.7904. Min Act: -0.0000

Data Index: 123911 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 2.7392. Min Range: -2.7392

Max Act: 1.8937. Min Act: -0.0000

Data Index: 553148 (C4 (Web Text))

Max Activating Token Index: 993