Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1709 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.3847. Min Act: -0.0000

Data Index: 23190 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.3585. Min Act: 0.0000

Data Index: 1353931 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.3216. Min Act: -0.0000

Data Index: 1027031 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1301300 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2617. Min Act: -0.0000

Data Index: 889911 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1252682 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2896. Min Act: -0.0000

Data Index: 58564 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2780. Min Act: -0.0000

Data Index: 786835 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2464. Min Act: -0.0000

Data Index: 1024051 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1328043 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2690. Min Act: -0.0000

Data Index: 1005340 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2584. Min Act: -0.0001

Data Index: 831393 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2603. Min Act: -0.0000

Data Index: 162579 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2593. Min Act: -0.0000

Data Index: 616263 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2338. Min Act: -0.0000

Data Index: 826507 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2424. Min Act: -0.0000

Data Index: 660964 (C4 (Web Text))

Max Activating Token Index: 142

Text #16

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2312. Min Act: -0.0000

Data Index: 48010 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2461. Min Act: -0.0000

Data Index: 615266 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2283. Min Act: -0.0000

Data Index: 5612 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.3847. Min Range: -0.3847

Max Act: 0.2615. Min Act: -0.0000

Data Index: 299077 (C4 (Web Text))

Max Activating Token Index: 873