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

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

Neuron 2074 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: 0.3529. Min Range: -0.3529

Max Act: 0.3327. Min Act: -0.0000

Data Index: 606086 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3289. Min Act: -0.0000

Data Index: 163805 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1116586 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3116. Min Act: -0.0000

Data Index: 392845 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3170. Min Act: -0.0000

Data Index: 441949 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3160. Min Act: -0.0000

Data Index: 541440 (C4 (Web Text))

Max Activating Token Index: 572

Text #6

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3205. Min Act: -0.0000

Data Index: 799097 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3041. Min Act: -0.0000

Data Index: 7383 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3529. Min Act: -0.0000

Data Index: 633381 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3020. Min Act: -0.0000

Data Index: 588947 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3168. Min Act: -0.0000

Data Index: 885936 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3037. Min Act: -0.0000

Data Index: 763907 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3038. Min Act: -0.0000

Data Index: 5212 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2994. Min Act: -0.0000

Data Index: 406940 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3293. Min Act: -0.0000

Data Index: 695682 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2971. Min Act: -0.0000

Data Index: 346526 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3067. Min Act: -0.0000

Data Index: 186262 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1316221 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.3074. Min Act: -0.0000

Data Index: 497853 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.3529. Min Range: -0.3529

Max Act: 0.2996. Min Act: -0.0000

Data Index: 370857 (C4 (Web Text))

Max Activating Token Index: 645