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

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

Neuron 1415 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.5369. Min Act: -0.0000

Data Index: 853034 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.5271. Min Act: -0.0000

Data Index: 1492303 (Python Code)

Max Activating Token Index: 351

Text #2

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.5451. Min Act: -0.0000

Data Index: 921090 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4948. Min Act: -0.0000

Data Index: 233860 (C4 (Web Text))

Max Activating Token Index: 392

Text #4

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1518492 (Python Code)

Max Activating Token Index: 472

Text #5

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4477. Min Act: -0.0000

Data Index: 378614 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1207005 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1319338 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4387. Min Act: -0.0000

Data Index: 150387 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1432183 (Python Code)

Max Activating Token Index: 133

Text #10

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4274. Min Act: -0.0000

Data Index: 45093 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1172597 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1363937 (Python Code)

Max Activating Token Index: 796

Text #13

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1545225 (Python Code)

Max Activating Token Index: 444

Text #14

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4218. Min Act: -0.0000

Data Index: 1260595 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4098. Min Act: -0.0000

Data Index: 686235 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4230. Min Act: -0.0000

Data Index: 989236 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4158. Min Act: -0.0000

Data Index: 267956 (C4 (Web Text))

Max Activating Token Index: 667

Text #18

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1492789 (Python Code)

Max Activating Token Index: 619

Text #19

Max Range: 0.5451. Min Range: -0.5451

Max Act: 0.3980. Min Act: -0.0000

Data Index: 1542190 (Python Code)

Max Activating Token Index: 835