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

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

Neuron 2272 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.4292. Min Act: -0.0002

Data Index: 828074 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.2798. Min Act: -0.0002

Data Index: 1165594 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.2436. Min Act: -0.0002

Data Index: 396624 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.2385. Min Act: -0.0002

Data Index: 490046 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.2383. Min Act: -0.0002

Data Index: 1121377 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.2280. Min Act: -0.0002

Data Index: 593712 (C4 (Web Text))

Max Activating Token Index: 468

Text #6

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.2287. Min Act: -0.0002

Data Index: 891143 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.2233. Min Act: -0.0003

Data Index: 712268 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.2173. Min Act: -0.0002

Data Index: 361731 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.2155. Min Act: -0.0003

Data Index: 648930 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.2062. Min Act: -0.0003

Data Index: 768236 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.2067. Min Act: -0.0002

Data Index: 1460725 (Python Code)

Max Activating Token Index: 745

Text #12

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.2041. Min Act: -0.0002

Data Index: 653577 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.1996. Min Act: -0.0002

Data Index: 625584 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.2013. Min Act: -0.0002

Data Index: 1130819 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.1980. Min Act: -0.0002

Data Index: 1395414 (Python Code)

Max Activating Token Index: 465

Text #16

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.2008. Min Act: -0.0002

Data Index: 548128 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.1996. Min Act: -0.0002

Data Index: 455714 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.1972. Min Act: -0.0002

Data Index: 722332 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.4292. Min Range: -0.4292

Max Act: 0.1999. Min Act: -0.0002

Data Index: 342218 (C4 (Web Text))

Max Activating Token Index: 680