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

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

Neuron 3803 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6830. Min Range: -2.6830

Max Act: 2.5287. Min Act: -0.0000

Data Index: 754305 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 2.6830. Min Range: -2.6830

Max Act: 2.6830. Min Act: -0.0000

Data Index: 1018130 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 2.6830. Min Range: -2.6830

Max Act: 2.2030. Min Act: -0.0000

Data Index: 939012 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 2.6830. Min Range: -2.6830

Max Act: 2.0515. Min Act: -0.0000

Data Index: 993811 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 2.6830. Min Range: -2.6830

Max Act: 1.9352. Min Act: -0.0000

Data Index: 341567 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 2.6830. Min Range: -2.6830

Max Act: 1.8702. Min Act: -0.0000

Data Index: 537187 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 2.6830. Min Range: -2.6830

Max Act: 1.8372. Min Act: -0.0000

Data Index: 1593280 (Python Code)

Max Activating Token Index: 163

Text #7

Max Range: 2.6830. Min Range: -2.6830

Max Act: 1.7582. Min Act: -0.0000

Data Index: 484701 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 2.6830. Min Range: -2.6830

Max Act: 1.6508. Min Act: -0.0000

Data Index: 334338 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 2.6830. Min Range: -2.6830

Max Act: 1.6978. Min Act: -0.0000

Data Index: 1295611 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 2.6830. Min Range: -2.6830

Max Act: 1.6996. Min Act: -0.0000

Data Index: 291836 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 2.6830. Min Range: -2.6830

Max Act: 1.6935. Min Act: -0.0000

Data Index: 288355 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 2.6830. Min Range: -2.6830

Max Act: 1.6683. Min Act: -0.0000

Data Index: 413610 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 2.6830. Min Range: -2.6830

Max Act: 1.6778. Min Act: -0.0000

Data Index: 967556 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 2.6830. Min Range: -2.6830

Max Act: 1.6631. Min Act: -0.0000

Data Index: 17183 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 2.6830. Min Range: -2.6830

Max Act: 1.7287. Min Act: -0.0000

Data Index: 159904 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 2.6830. Min Range: -2.6830

Max Act: 1.5300. Min Act: -0.0000

Data Index: 164211 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 2.6830. Min Range: -2.6830

Max Act: 1.7310. Min Act: -0.0000

Data Index: 1191496 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 2.6830. Min Range: -2.6830

Max Act: 1.5683. Min Act: -0.0000

Data Index: 995477 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 2.6830. Min Range: -2.6830

Max Act: 1.4897. Min Act: -0.0000

Data Index: 925028 (C4 (Web Text))

Max Activating Token Index: 423