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

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

Neuron 3220 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: 0.6379. Min Range: -0.6379

Max Act: 0.6379. Min Act: -0.0000

Data Index: 33223 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1097284 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1248866 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5260. Min Act: -0.0000

Data Index: 1231255 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4790. Min Act: -0.0000

Data Index: 655878 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1151091 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4661. Min Act: -0.0000

Data Index: 215798 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4780. Min Act: -0.0000

Data Index: 71765 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4576. Min Act: -0.0000

Data Index: 714237 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4349. Min Act: -0.0000

Data Index: 546764 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4410. Min Act: -0.0000

Data Index: 431416 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4665. Min Act: -0.0000

Data Index: 619175 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4600. Min Act: -0.0000

Data Index: 301045 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4370. Min Act: -0.0000

Data Index: 27824 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4243. Min Act: -0.0000

Data Index: 898496 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4315. Min Act: -0.0000

Data Index: 515286 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1286215 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4104. Min Act: -0.0000

Data Index: 772277 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4250. Min Act: -0.0000

Data Index: 289252 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4186. Min Act: -0.0000

Data Index: 645548 (C4 (Web Text))

Max Activating Token Index: 232