Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4919 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.3033. Min Range: -5.3033

Max Act: 5.3033. Min Act: -0.0000

Data Index: 31984 (C4 (Web Text))

Max Activating Token Index: 789

Text #1

Max Range: 5.3033. Min Range: -5.3033

Max Act: 5.0572. Min Act: -0.0000

Data Index: 1288071 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 5.3033. Min Range: -5.3033

Max Act: 4.7335. Min Act: -0.0000

Data Index: 69344 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 5.3033. Min Range: -5.3033

Max Act: 4.4207. Min Act: -0.0000

Data Index: 1188713 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 5.3033. Min Range: -5.3033

Max Act: 4.0326. Min Act: -0.0000

Data Index: 395624 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 5.3033. Min Range: -5.3033

Max Act: 4.4397. Min Act: -0.0000

Data Index: 448692 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 5.3033. Min Range: -5.3033

Max Act: 4.0814. Min Act: -0.0000

Data Index: 967419 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 5.3033. Min Range: -5.3033

Max Act: 4.0832. Min Act: -0.0000

Data Index: 184813 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 5.3033. Min Range: -5.3033

Max Act: 4.0206. Min Act: -0.0000

Data Index: 773628 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 5.3033. Min Range: -5.3033

Max Act: 3.9934. Min Act: -0.0000

Data Index: 1179978 (C4 (Web Text))

Max Activating Token Index: 26

Text #10

Max Range: 5.3033. Min Range: -5.3033

Max Act: 4.1687. Min Act: -0.0000

Data Index: 610753 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 5.3033. Min Range: -5.3033

Max Act: 4.1080. Min Act: -0.0000

Data Index: 1320156 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 5.3033. Min Range: -5.3033

Max Act: 3.7403. Min Act: -0.0000

Data Index: 1144559 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 5.3033. Min Range: -5.3033

Max Act: 4.0620. Min Act: -0.0000

Data Index: 926770 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 5.3033. Min Range: -5.3033

Max Act: 3.8650. Min Act: -0.0000

Data Index: 1238778 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 5.3033. Min Range: -5.3033

Max Act: 3.9630. Min Act: -0.0000

Data Index: 534585 (C4 (Web Text))

Max Activating Token Index: 488

Text #16

Max Range: 5.3033. Min Range: -5.3033

Max Act: 4.0012. Min Act: -0.0000

Data Index: 575724 (C4 (Web Text))

Max Activating Token Index: 330

Text #17

Max Range: 5.3033. Min Range: -5.3033

Max Act: 3.5890. Min Act: -0.0000

Data Index: 670883 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 5.3033. Min Range: -5.3033

Max Act: 3.6217. Min Act: -0.0000

Data Index: 742424 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 5.3033. Min Range: -5.3033

Max Act: 3.5804. Min Act: -0.0000

Data Index: 13455 (C4 (Web Text))

Max Activating Token Index: 566