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

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

Neuron 4619 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: 0.7627. Min Range: -0.7627

Max Act: 0.7627. Min Act: -0.0002

Data Index: 423147 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.6439. Min Act: -0.0002

Data Index: 1133375 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.6351. Min Act: -0.0002

Data Index: 744768 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.6150. Min Act: -0.0002

Data Index: 1139988 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.5821. Min Act: -0.0002

Data Index: 268796 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.5877. Min Act: -0.0002

Data Index: 1323331 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.5468. Min Act: -0.0002

Data Index: 672742 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.5635. Min Act: -0.0002

Data Index: 1112246 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.5407. Min Act: -0.0002

Data Index: 1301349 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.5510. Min Act: -0.0002

Data Index: 152398 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.5361. Min Act: -0.0002

Data Index: 241162 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.5343. Min Act: -0.0002

Data Index: 592389 (C4 (Web Text))

Max Activating Token Index: 471

Text #12

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.5244. Min Act: -0.0002

Data Index: 1151611 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.5294. Min Act: -0.0002

Data Index: 1010229 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.5188. Min Act: -0.0002

Data Index: 542830 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.4967. Min Act: -0.0002

Data Index: 729348 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.4585. Min Act: -0.0002

Data Index: 684199 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.4488. Min Act: -0.0002

Data Index: 345297 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.3939. Min Act: -0.0002

Data Index: 813461 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.7627. Min Range: -0.7627

Max Act: 0.3901. Min Act: -0.0002

Data Index: 638030 (C4 (Web Text))

Max Activating Token Index: 6