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

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

Neuron 1233 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0773. Min Range: -1.0773

Max Act: 1.0186. Min Act: -0.0000

Data Index: 306395 (C4 (Web Text))

Max Activating Token Index: 313

Text #1

Max Range: 1.0773. Min Range: -1.0773

Max Act: 1.0773. Min Act: -0.0000

Data Index: 272207 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9715. Min Act: -0.0000

Data Index: 141687 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 1.0773. Min Range: -1.0773

Max Act: 1.0118. Min Act: -0.0000

Data Index: 406755 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9564. Min Act: -0.0000

Data Index: 374900 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1294705 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9333. Min Act: -0.0000

Data Index: 894008 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9273. Min Act: -0.0000

Data Index: 1129056 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.9038. Min Act: -0.0000

Data Index: 1166880 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8993. Min Act: -0.0000

Data Index: 768834 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1269749 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8011. Min Act: -0.0000

Data Index: 183290 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8165. Min Act: -0.0000

Data Index: 161686 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.7916. Min Act: -0.0000

Data Index: 32613 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8319. Min Act: -0.0000

Data Index: 45649 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1085900 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8194. Min Act: -0.0000

Data Index: 914323 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8268. Min Act: -0.0000

Data Index: 1110921 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8716. Min Act: -0.0000

Data Index: 1209938 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 1.0773. Min Range: -1.0773

Max Act: 0.8084. Min Act: -0.0000

Data Index: 535941 (C4 (Web Text))

Max Activating Token Index: 888