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

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

Neuron 1314 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: 6.6757. Min Range: -6.6757

Max Act: 6.6757. Min Act: -0.0000

Data Index: 1074154 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 6.6757. Min Range: -6.6757

Max Act: 6.6362. Min Act: -0.0000

Data Index: 982353 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 6.6757. Min Range: -6.6757

Max Act: 5.9050. Min Act: -0.0000

Data Index: 434364 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 6.6757. Min Range: -6.6757

Max Act: 5.5038. Min Act: -0.0000

Data Index: 636831 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 6.6757. Min Range: -6.6757

Max Act: 5.6218. Min Act: -0.0000

Data Index: 518300 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 6.6757. Min Range: -6.6757

Max Act: 5.0586. Min Act: -0.0000

Data Index: 1136761 (C4 (Web Text))

Max Activating Token Index: 943

Text #6

Max Range: 6.6757. Min Range: -6.6757

Max Act: 4.5930. Min Act: -0.0000

Data Index: 828484 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 6.6757. Min Range: -6.6757

Max Act: 4.2216. Min Act: -0.0000

Data Index: 937448 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 6.6757. Min Range: -6.6757

Max Act: 4.3327. Min Act: -0.0000

Data Index: 700282 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 6.6757. Min Range: -6.6757

Max Act: 4.4338. Min Act: -0.0000

Data Index: 902994 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 6.6757. Min Range: -6.6757

Max Act: 4.1374. Min Act: -0.0000

Data Index: 1225542 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 6.6757. Min Range: -6.6757

Max Act: 3.8781. Min Act: -0.0000

Data Index: 336187 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 6.6757. Min Range: -6.6757

Max Act: 3.6826. Min Act: -0.0000

Data Index: 967241 (C4 (Web Text))

Max Activating Token Index: 141

Text #13

Max Range: 6.6757. Min Range: -6.6757

Max Act: 3.7435. Min Act: -0.0000

Data Index: 835338 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 6.6757. Min Range: -6.6757

Max Act: 3.5383. Min Act: -0.0000

Data Index: 486020 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 6.6757. Min Range: -6.6757

Max Act: 3.6290. Min Act: -0.0000

Data Index: 328170 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 6.6757. Min Range: -6.6757

Max Act: 3.5120. Min Act: -0.0000

Data Index: 608939 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 6.6757. Min Range: -6.6757

Max Act: 3.4689. Min Act: -0.0000

Data Index: 898382 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 6.6757. Min Range: -6.6757

Max Act: 3.8799. Min Act: -0.0000

Data Index: 184568 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 6.6757. Min Range: -6.6757

Max Act: 3.7027. Min Act: -0.0000

Data Index: 1349244 (C4 (Web Text))

Max Activating Token Index: 813