Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 810 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1637330 (Python Code)

Max Activating Token Index: 680

Text #1

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5980. Min Act: 0.0000

Data Index: 1414737 (Python Code)

Max Activating Token Index: 611

Text #2

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5884. Min Act: -0.0001

Data Index: 1637063 (Python Code)

Max Activating Token Index: 121

Text #3

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6063. Min Act: 0.0000

Data Index: 1377923 (Python Code)

Max Activating Token Index: 222

Text #4

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5342. Min Act: -0.0000

Data Index: 463521 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5384. Min Act: -0.0000

Data Index: 173883 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5276. Min Act: -0.0000

Data Index: 48394 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5259. Min Act: 0.0000

Data Index: 1533818 (Python Code)

Max Activating Token Index: 79

Text #8

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5035. Min Act: -0.0000

Data Index: 1277646 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5027. Min Act: 0.0000

Data Index: 1587307 (Python Code)

Max Activating Token Index: 869

Text #10

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5082. Min Act: -0.0000

Data Index: 217383 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1277078 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4849. Min Act: -0.0000

Data Index: 745788 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4698. Min Act: -0.0001

Data Index: 474222 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4985. Min Act: -0.0000

Data Index: 836734 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4759. Min Act: 0.0001

Data Index: 244222 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1027240 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4519. Min Act: -0.0000

Data Index: 35346 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4335. Min Act: -0.0000

Data Index: 97060 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.4388. Min Act: -0.0001

Data Index: 15770 (C4 (Web Text))

Max Activating Token Index: 80