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

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

Neuron 1617 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.8648. Min Act: -0.0001

Data Index: 1561902 (Python Code)

Max Activating Token Index: 206

Text #1

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.6077. Min Act: -0.0001

Data Index: 1353560 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.5468. Min Act: -0.0001

Data Index: 185142 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.5670. Min Act: -0.0001

Data Index: 1170905 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.3820. Min Act: -0.0001

Data Index: 533926 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.4436. Min Act: -0.0001

Data Index: 1126642 (C4 (Web Text))

Max Activating Token Index: 999

Text #6

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.4974. Min Act: -0.0001

Data Index: 1003842 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.3334. Min Act: -0.0001

Data Index: 539568 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.3972. Min Act: -0.0001

Data Index: 1257102 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.4715. Min Act: -0.0001

Data Index: 309593 (C4 (Web Text))

Max Activating Token Index: 173

Text #10

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.4144. Min Act: -0.0001

Data Index: 1521577 (Python Code)

Max Activating Token Index: 455

Text #11

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.2792. Min Act: -0.0001

Data Index: 729683 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.3609. Min Act: -0.0001

Data Index: 941421 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.3658. Min Act: -0.0001

Data Index: 173325 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.3550. Min Act: -0.0001

Data Index: 475478 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.3753. Min Act: -0.0001

Data Index: 150121 (C4 (Web Text))

Max Activating Token Index: 4

Text #16

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.3267. Min Act: -0.0001

Data Index: 609943 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.3035. Min Act: -0.0001

Data Index: 316855 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.3286. Min Act: -0.0001

Data Index: 533940 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 1.8648. Min Range: -1.8648

Max Act: 1.3277. Min Act: -0.0001

Data Index: 811942 (C4 (Web Text))

Max Activating Token Index: 559