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

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

Neuron 1332 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.7764. Min Act: -0.0000

Data Index: 674604 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.6953. Min Act: -0.0000

Data Index: 1262338 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.5744. Min Act: -0.0000

Data Index: 38868 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.8149. Min Act: -0.0000

Data Index: 789786 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.6488. Min Act: -0.0000

Data Index: 356998 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.6126. Min Act: -0.0000

Data Index: 507104 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.4970. Min Act: -0.0000

Data Index: 37422 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.6333. Min Act: -0.0000

Data Index: 62998 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.4756. Min Act: -0.0000

Data Index: 957038 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.5314. Min Act: -0.0000

Data Index: 347499 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.5306. Min Act: -0.0000

Data Index: 461301 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.3532. Min Act: -0.0000

Data Index: 286303 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.3315. Min Act: -0.0000

Data Index: 282396 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.3228. Min Act: -0.0000

Data Index: 448816 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.2845. Min Act: -0.0000

Data Index: 770465 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.2919. Min Act: -0.0000

Data Index: 444054 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.2104. Min Act: -0.0000

Data Index: 916493 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.2186. Min Act: -0.0000

Data Index: 1001353 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.1737. Min Act: -0.0000

Data Index: 49220 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 2.8149. Min Range: -2.8149

Max Act: 2.2499. Min Act: -0.0000

Data Index: 725230 (C4 (Web Text))

Max Activating Token Index: 707