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

Dataset: The Pile

Neuron 2147 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2421. Min Range: -1.2421

Max Act: 1.0978. Min Act: -0.0000

Data Index: 1073801 (The Pile)

Max Activating Token Index: 509

Text #1

Max Range: 1.2421. Min Range: -1.2421

Max Act: 1.2421. Min Act: -0.0000

Data Index: 1019173 (The Pile)

Max Activating Token Index: 572

Text #2

Max Range: 1.2421. Min Range: -1.2421

Max Act: 1.1834. Min Act: -0.0000

Data Index: 701153 (The Pile)

Max Activating Token Index: 224

Text #3

Max Range: 1.2421. Min Range: -1.2421

Max Act: 1.1067. Min Act: -0.0000

Data Index: 1083990 (The Pile)

Max Activating Token Index: 320

Text #4

Max Range: 1.2421. Min Range: -1.2421

Max Act: 1.1005. Min Act: -0.0000

Data Index: 1373692 (The Pile)

Max Activating Token Index: 480

Text #5

Max Range: 1.2421. Min Range: -1.2421

Max Act: 1.0978. Min Act: -0.0000

Data Index: 943206 (The Pile)

Max Activating Token Index: 328

Text #6

Max Range: 1.2421. Min Range: -1.2421

Max Act: 1.0262. Min Act: -0.0000

Data Index: 949646 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 1.2421. Min Range: -1.2421

Max Act: 1.1089. Min Act: -0.0000

Data Index: 1130082 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 1.2421. Min Range: -1.2421

Max Act: 1.0383. Min Act: -0.0000

Data Index: 914256 (The Pile)

Max Activating Token Index: 619

Text #9

Max Range: 1.2421. Min Range: -1.2421

Max Act: 0.9825. Min Act: -0.0000

Data Index: 760515 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 1.2421. Min Range: -1.2421

Max Act: 0.9728. Min Act: -0.0000

Data Index: 375297 (The Pile)

Max Activating Token Index: 524

Text #11

Max Range: 1.2421. Min Range: -1.2421

Max Act: 1.0003. Min Act: -0.0000

Data Index: 809235 (The Pile)

Max Activating Token Index: 1001

Text #12

Max Range: 1.2421. Min Range: -1.2421

Max Act: 0.9353. Min Act: -0.0000

Data Index: 328179 (The Pile)

Max Activating Token Index: 424

Text #13

Max Range: 1.2421. Min Range: -1.2421

Max Act: 0.9301. Min Act: -0.0000

Data Index: 783502 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 1.2421. Min Range: -1.2421

Max Act: 0.9238. Min Act: -0.0000

Data Index: 1916290 (The Pile)

Max Activating Token Index: 421

Text #15

Max Range: 1.2421. Min Range: -1.2421

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1966348 (The Pile)

Max Activating Token Index: 350

Text #16

Max Range: 1.2421. Min Range: -1.2421

Max Act: 0.9465. Min Act: -0.0000

Data Index: 1328558 (The Pile)

Max Activating Token Index: 749

Text #17

Max Range: 1.2421. Min Range: -1.2421

Max Act: 0.8814. Min Act: -0.0000

Data Index: 880248 (The Pile)

Max Activating Token Index: 576

Text #18

Max Range: 1.2421. Min Range: -1.2421

Max Act: 0.9346. Min Act: -0.0000

Data Index: 396400 (The Pile)

Max Activating Token Index: 374

Text #19

Max Range: 1.2421. Min Range: -1.2421

Max Act: 0.9091. Min Act: -0.0000

Data Index: 370668 (The Pile)

Max Activating Token Index: 618