Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3248 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.6277. Min Act: -0.0000

Data Index: 676160 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1061334 (C4 (Web Text))

Max Activating Token Index: 935

Text #2

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.5645. Min Act: -0.0000

Data Index: 500720 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.5273. Min Act: -0.0000

Data Index: 783799 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.5212. Min Act: -0.0000

Data Index: 681081 (C4 (Web Text))

Max Activating Token Index: 236

Text #5

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1655243 (Python Code)

Max Activating Token Index: 705

Text #6

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.4637. Min Act: -0.0000

Data Index: 977844 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.4751. Min Act: -0.0000

Data Index: 600093 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.4655. Min Act: -0.0000

Data Index: 1030507 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.4391. Min Act: -0.0000

Data Index: 347448 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.4270. Min Act: -0.0000

Data Index: 1159418 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.4293. Min Act: -0.0000

Data Index: 699928 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1279254 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1302409 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.4153. Min Act: -0.0000

Data Index: 488295 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.4008. Min Act: -0.0000

Data Index: 403802 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.3818. Min Act: -0.0000

Data Index: 182900 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.3940. Min Act: -0.0000

Data Index: 1295108 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1037939 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.6277. Min Range: -0.6277

Max Act: 0.3889. Min Act: -0.0000

Data Index: 882740 (C4 (Web Text))

Max Activating Token Index: 219