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

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

Neuron 1256 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: 1.9748. Min Range: -1.9748

Max Act: 1.9748. Min Act: -0.0000

Data Index: 539814 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.8562. Min Act: -0.0000

Data Index: 1353599 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.7222. Min Act: -0.0000

Data Index: 341406 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.7186. Min Act: -0.0000

Data Index: 446083 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.8086. Min Act: -0.0000

Data Index: 982566 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.8022. Min Act: -0.0000

Data Index: 1010308 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.7967. Min Act: -0.0000

Data Index: 125414 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.8967. Min Act: -0.0000

Data Index: 1266455 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.8397. Min Act: -0.0000

Data Index: 569422 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.6600. Min Act: -0.0000

Data Index: 224280 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.7313. Min Act: -0.0000

Data Index: 674814 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.6071. Min Act: -0.0000

Data Index: 30136 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.7625. Min Act: -0.0000

Data Index: 777433 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.6055. Min Act: -0.0000

Data Index: 352481 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.5286. Min Act: -0.0000

Data Index: 1334976 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.5978. Min Act: -0.0000

Data Index: 362873 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.4951. Min Act: -0.0000

Data Index: 953907 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.6875. Min Act: -0.0000

Data Index: 1247542 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.5763. Min Act: -0.0000

Data Index: 996898 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.9748. Min Range: -1.9748

Max Act: 1.4945. Min Act: -0.0000

Data Index: 1357028 (C4 (Web Text))

Max Activating Token Index: 828