Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3500 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3729. Min Act: -0.0002

Data Index: 762692 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3161. Min Act: -0.0001

Data Index: 1146160 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3281. Min Act: -0.0002

Data Index: 435618 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3098. Min Act: -0.0001

Data Index: 837464 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.2623. Min Act: -0.0002

Data Index: 446402 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.2840. Min Act: -0.0002

Data Index: 225481 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.2064. Min Act: -0.0001

Data Index: 711149 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.2410. Min Act: -0.0002

Data Index: 1211303 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3152. Min Act: -0.0001

Data Index: 1335614 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.2651. Min Act: -0.0001

Data Index: 436794 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3003. Min Act: -0.0001

Data Index: 410518 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.2845. Min Act: -0.0002

Data Index: 799640 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.3188. Min Act: -0.0002

Data Index: 1191646 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.2143. Min Act: -0.0002

Data Index: 801582 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.2430. Min Act: -0.0002

Data Index: 157391 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.2696. Min Act: -0.0002

Data Index: 822807 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.2397. Min Act: -0.0002

Data Index: 793843 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.2349. Min Act: -0.0002

Data Index: 605800 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.1325. Min Act: -0.0002

Data Index: 349027 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.1819. Min Act: -0.0002

Data Index: 159613 (C4 (Web Text))

Max Activating Token Index: 724