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

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

Neuron 1824 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2258. Min Range: -5.2258

Max Act: 5.2258. Min Act: -0.0001

Data Index: 96064 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 5.2258. Min Range: -5.2258

Max Act: 5.0821. Min Act: -0.0001

Data Index: 1251126 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.3275. Min Act: -0.0001

Data Index: 717937 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.4011. Min Act: -0.0001

Data Index: 687479 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.3194. Min Act: -0.0001

Data Index: 702546 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 5.2258. Min Range: -5.2258

Max Act: 3.9050. Min Act: -0.0001

Data Index: 733462 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.0430. Min Act: -0.0001

Data Index: 240035 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 5.2258. Min Range: -5.2258

Max Act: 3.8032. Min Act: -0.0001

Data Index: 972214 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.3958. Min Act: -0.0001

Data Index: 99526 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 5.2258. Min Range: -5.2258

Max Act: 3.8684. Min Act: -0.0001

Data Index: 1112644 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.0585. Min Act: -0.0001

Data Index: 320187 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 5.2258. Min Range: -5.2258

Max Act: 3.7531. Min Act: -0.0001

Data Index: 1178713 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 5.2258. Min Range: -5.2258

Max Act: 4.0295. Min Act: -0.0001

Data Index: 934924 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 5.2258. Min Range: -5.2258

Max Act: 3.8059. Min Act: -0.0001

Data Index: 14522 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 5.2258. Min Range: -5.2258

Max Act: 3.6900. Min Act: -0.0001

Data Index: 666495 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 5.2258. Min Range: -5.2258

Max Act: 3.6627. Min Act: -0.0001

Data Index: 743035 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 5.2258. Min Range: -5.2258

Max Act: 3.3115. Min Act: -0.0001

Data Index: 1267124 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 5.2258. Min Range: -5.2258

Max Act: 3.6513. Min Act: -0.0001

Data Index: 59333 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 5.2258. Min Range: -5.2258

Max Act: 3.5429. Min Act: -0.0001

Data Index: 274156 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 5.2258. Min Range: -5.2258

Max Act: 3.5507. Min Act: -0.0001

Data Index: 264296 (C4 (Web Text))

Max Activating Token Index: 823