Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1209 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0405. Min Act: -0.0004

Data Index: 9449 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0385. Min Act: -0.0003

Data Index: 478197 (C4 (Web Text))

Max Activating Token Index: 659

Text #2

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0365. Min Act: -0.0003

Data Index: 831207 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0372. Min Act: -0.0003

Data Index: 497594 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0365. Min Act: -0.0003

Data Index: 312966 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0361. Min Act: -0.0003

Data Index: 1043417 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0365. Min Act: -0.0003

Data Index: 701741 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0366. Min Act: -0.0003

Data Index: 1234382 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0357. Min Act: -0.0003

Data Index: 778094 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0350. Min Act: -0.0004

Data Index: 565194 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0350. Min Act: -0.0003

Data Index: 698807 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0347. Min Act: -0.0003

Data Index: 606288 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0354. Min Act: -0.0003

Data Index: 180241 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0352. Min Act: -0.0003

Data Index: 526985 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0343. Min Act: -0.0003

Data Index: 2208 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0342. Min Act: -0.0003

Data Index: 280128 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1027374 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0321. Min Act: -0.0004

Data Index: 632407 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0323. Min Act: -0.0003

Data Index: 840014 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0322. Min Act: -0.0003

Data Index: 598364 (C4 (Web Text))

Max Activating Token Index: 262