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

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

Neuron 1087 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: 6.2823. Min Range: -6.2823

Max Act: 6.1414. Min Act: -0.0000

Data Index: 682901 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 6.2823. Min Range: -6.2823

Max Act: 6.2823. Min Act: -0.0000

Data Index: 310157 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.8404. Min Act: -0.0000

Data Index: 96405 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.8548. Min Act: -0.0000

Data Index: 1309172 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.3256. Min Act: -0.0000

Data Index: 1183902 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.6235. Min Act: -0.0000

Data Index: 640618 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.6658. Min Act: -0.0000

Data Index: 592931 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.7168. Min Act: -0.0000

Data Index: 387834 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.7682. Min Act: -0.0000

Data Index: 87459 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.5177. Min Act: -0.0000

Data Index: 560410 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.7175. Min Act: -0.0000

Data Index: 213981 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.6484. Min Act: -0.0000

Data Index: 696588 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.1879. Min Act: -0.0000

Data Index: 446216 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.5713. Min Act: -0.0000

Data Index: 128156 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.1873. Min Act: -0.0000

Data Index: 851751 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.4161. Min Act: -0.0000

Data Index: 840050 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.2576. Min Act: -0.0000

Data Index: 488715 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.2698. Min Act: -0.0000

Data Index: 420471 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.2311. Min Act: -0.0000

Data Index: 1250724 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 6.2823. Min Range: -6.2823

Max Act: 5.4586. Min Act: -0.0000

Data Index: 213225 (C4 (Web Text))

Max Activating Token Index: 508