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

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

Neuron 4272 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1901. Min Range: -2.1901

Max Act: 2.1434. Min Act: -0.0000

Data Index: 649781 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 2.1901. Min Range: -2.1901

Max Act: 2.1901. Min Act: -0.0000

Data Index: 277373 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.8618. Min Act: -0.0000

Data Index: 1351973 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.9817. Min Act: -0.0000

Data Index: 674907 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.6775. Min Act: -0.0000

Data Index: 463021 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.8498. Min Act: -0.0000

Data Index: 101358 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.6863. Min Act: -0.0000

Data Index: 469697 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.8213. Min Act: -0.0000

Data Index: 385413 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.6830. Min Act: -0.0000

Data Index: 877872 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.6757. Min Act: -0.0000

Data Index: 125588 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.7298. Min Act: -0.0000

Data Index: 245169 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.7619. Min Act: -0.0000

Data Index: 438708 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.7739. Min Act: -0.0000

Data Index: 1084055 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.6327. Min Act: -0.0000

Data Index: 837204 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.6162. Min Act: -0.0000

Data Index: 514194 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.5813. Min Act: -0.0000

Data Index: 489809 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.5103. Min Act: -0.0000

Data Index: 488318 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.5974. Min Act: -0.0000

Data Index: 178169 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.6192. Min Act: -0.0000

Data Index: 792061 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 2.1901. Min Range: -2.1901

Max Act: 1.5457. Min Act: -0.0000

Data Index: 701092 (C4 (Web Text))

Max Activating Token Index: 437