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

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

Neuron 4867 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.6459. Min Act: -0.0000

Data Index: 11212 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.6292. Min Act: -0.0000

Data Index: 676599 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1600643 (Python Code)

Max Activating Token Index: 255

Text #3

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1627105 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1636322 (Python Code)

Max Activating Token Index: 144

Text #5

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5452. Min Act: -0.0000

Data Index: 1531016 (Python Code)

Max Activating Token Index: 272

Text #6

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.4838. Min Act: -0.0000

Data Index: 882697 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1379247 (Python Code)

Max Activating Token Index: 255

Text #8

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1362669 (Python Code)

Max Activating Token Index: 314

Text #9

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.4947. Min Act: -0.0000

Data Index: 326701 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1411992 (Python Code)

Max Activating Token Index: 172

Text #11

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5109. Min Act: -0.0000

Data Index: 535454 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1359991 (Python Code)

Max Activating Token Index: 375

Text #13

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1613621 (Python Code)

Max Activating Token Index: 762

Text #14

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.5018. Min Act: -0.0000

Data Index: 210910 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.4838. Min Act: -0.0000

Data Index: 754100 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.4376. Min Act: -0.0000

Data Index: 387173 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.4466. Min Act: -0.0000

Data Index: 184549 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.4791. Min Act: -0.0000

Data Index: 159756 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 0.6459. Min Range: -0.6459

Max Act: 0.4904. Min Act: -0.0000

Data Index: 1653386 (Python Code)

Max Activating Token Index: 446