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

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

Neuron 4283 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.9879. Min Act: -0.0000

Data Index: 851540 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.9896. Min Act: -0.0000

Data Index: 440887 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.7965. Min Act: -0.0000

Data Index: 1036135 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.8238. Min Act: -0.0000

Data Index: 1038349 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.6726. Min Act: -0.0000

Data Index: 409592 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.6056. Min Act: -0.0000

Data Index: 475832 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.5997. Min Act: -0.0000

Data Index: 860772 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.7183. Min Act: -0.0000

Data Index: 773887 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.5749. Min Act: -0.0000

Data Index: 1206127 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.4417. Min Act: -0.0000

Data Index: 245038 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.1700. Min Act: -0.0000

Data Index: 173010 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.3575. Min Act: -0.0000

Data Index: 1182690 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 2.9896. Min Range: -2.9896

Max Act: 1.9630. Min Act: -0.0000

Data Index: 1086987 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 2.9896. Min Range: -2.9896

Max Act: 1.9962. Min Act: -0.0000

Data Index: 1182332 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.5905. Min Act: -0.0000

Data Index: 1117668 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.0712. Min Act: -0.0000

Data Index: 405016 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.1532. Min Act: -0.0000

Data Index: 769950 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.2586. Min Act: -0.0000

Data Index: 306854 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.3279. Min Act: -0.0000

Data Index: 858388 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 2.9896. Min Range: -2.9896

Max Act: 2.0953. Min Act: -0.0000

Data Index: 866978 (C4 (Web Text))

Max Activating Token Index: 831