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

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

Neuron 4397 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.7615. Min Act: -0.0000

Data Index: 1477394 (Python Code)

Max Activating Token Index: 116

Text #1

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.6142. Min Act: -0.0000

Data Index: 1409405 (Python Code)

Max Activating Token Index: 473

Text #2

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1389669 (Python Code)

Max Activating Token Index: 369

Text #3

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1253435 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1474791 (Python Code)

Max Activating Token Index: 216

Text #5

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5384. Min Act: -0.0001

Data Index: 1338593 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5621. Min Act: -0.0000

Data Index: 766287 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5385. Min Act: -0.0000

Data Index: 1620333 (Python Code)

Max Activating Token Index: 935

Text #8

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5532. Min Act: -0.0000

Data Index: 653979 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4847. Min Act: -0.0001

Data Index: 1099547 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5339. Min Act: -0.0001

Data Index: 1313775 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1383833 (Python Code)

Max Activating Token Index: 262

Text #12

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1454959 (Python Code)

Max Activating Token Index: 290

Text #13

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5122. Min Act: -0.0000

Data Index: 379006 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1519481 (Python Code)

Max Activating Token Index: 471

Text #15

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4704. Min Act: -0.0000

Data Index: 1643772 (Python Code)

Max Activating Token Index: 906

Text #16

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1360765 (Python Code)

Max Activating Token Index: 40

Text #17

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4915. Min Act: -0.0000

Data Index: 172891 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4581. Min Act: -0.0000

Data Index: 1515408 (Python Code)

Max Activating Token Index: 408

Text #19

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4943. Min Act: -0.0001

Data Index: 371760 (C4 (Web Text))

Max Activating Token Index: 497