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

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

Neuron 2623 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: 1.7128. Min Range: -1.7128

Max Act: 1.7128. Min Act: -0.0000

Data Index: 1029548 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.5313. Min Act: -0.0000

Data Index: 1250196 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.5318. Min Act: -0.0000

Data Index: 1275265 (C4 (Web Text))

Max Activating Token Index: 265

Text #3

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.4523. Min Act: -0.0000

Data Index: 312762 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.2922. Min Act: -0.0000

Data Index: 317208 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.3620. Min Act: -0.0000

Data Index: 581696 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.3526. Min Act: -0.0000

Data Index: 1000030 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.3412. Min Act: -0.0000

Data Index: 159244 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.3145. Min Act: -0.0000

Data Index: 1162600 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.2865. Min Act: -0.0000

Data Index: 411548 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.2803. Min Act: -0.0000

Data Index: 652781 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.2195. Min Act: -0.0000

Data Index: 607170 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.2111. Min Act: -0.0000

Data Index: 336196 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.1287. Min Act: -0.0000

Data Index: 498226 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.1386. Min Act: -0.0000

Data Index: 1258103 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.1219. Min Act: -0.0000

Data Index: 1094 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.1051. Min Act: -0.0000

Data Index: 1213534 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.1077. Min Act: -0.0000

Data Index: 540456 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.0960. Min Act: -0.0000

Data Index: 868275 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 1.7128. Min Range: -1.7128

Max Act: 1.1470. Min Act: -0.0000

Data Index: 212630 (C4 (Web Text))

Max Activating Token Index: 175