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

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

Neuron 1802 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9352. Min Range: -6.9352

Max Act: 6.9352. Min Act: -0.0000

Data Index: 472018 (C4 (Web Text))

Max Activating Token Index: 539

Text #1

Max Range: 6.9352. Min Range: -6.9352

Max Act: 6.5045. Min Act: -0.0000

Data Index: 642798 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 6.9352. Min Range: -6.9352

Max Act: 6.5989. Min Act: -0.0000

Data Index: 62873 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 6.9352. Min Range: -6.9352

Max Act: 6.2487. Min Act: -0.0000

Data Index: 45860 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 6.9352. Min Range: -6.9352

Max Act: 6.2850. Min Act: -0.0000

Data Index: 1274453 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 6.9352. Min Range: -6.9352

Max Act: 5.7180. Min Act: -0.0000

Data Index: 395989 (C4 (Web Text))

Max Activating Token Index: 101

Text #6

Max Range: 6.9352. Min Range: -6.9352

Max Act: 5.9011. Min Act: -0.0000

Data Index: 457222 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 6.9352. Min Range: -6.9352

Max Act: 5.5663. Min Act: -0.0000

Data Index: 1119023 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 6.9352. Min Range: -6.9352

Max Act: 5.5617. Min Act: -0.0000

Data Index: 1357204 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 6.9352. Min Range: -6.9352

Max Act: 5.6334. Min Act: -0.0000

Data Index: 53419 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 6.9352. Min Range: -6.9352

Max Act: 5.6381. Min Act: -0.0000

Data Index: 696995 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 6.9352. Min Range: -6.9352

Max Act: 5.7264. Min Act: -0.0000

Data Index: 367730 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 6.9352. Min Range: -6.9352

Max Act: 5.5382. Min Act: -0.0000

Data Index: 118609 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 6.9352. Min Range: -6.9352

Max Act: 5.4962. Min Act: -0.0000

Data Index: 669909 (C4 (Web Text))

Max Activating Token Index: 959

Text #14

Max Range: 6.9352. Min Range: -6.9352

Max Act: 5.4800. Min Act: -0.0000

Data Index: 485389 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 6.9352. Min Range: -6.9352

Max Act: 5.2496. Min Act: -0.0000

Data Index: 186684 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 6.9352. Min Range: -6.9352

Max Act: 5.4247. Min Act: -0.0000

Data Index: 347182 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 6.9352. Min Range: -6.9352

Max Act: 5.2267. Min Act: -0.0000

Data Index: 1171024 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 6.9352. Min Range: -6.9352

Max Act: 5.5762. Min Act: -0.0000

Data Index: 129040 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 6.9352. Min Range: -6.9352

Max Act: 5.3923. Min Act: -0.0000

Data Index: 868825 (C4 (Web Text))

Max Activating Token Index: 24