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

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

Neuron 1595 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.7209. Min Act: -0.0001

Data Index: 881461 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.7321. Min Act: -0.0001

Data Index: 329214 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6863. Min Act: -0.0001

Data Index: 1302334 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.7130. Min Act: -0.0001

Data Index: 1345474 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6450. Min Act: -0.0001

Data Index: 215706 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.5980. Min Act: -0.0001

Data Index: 340591 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6227. Min Act: -0.0001

Data Index: 1343446 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6156. Min Act: -0.0001

Data Index: 953089 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6182. Min Act: -0.0001

Data Index: 884494 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6536. Min Act: -0.0001

Data Index: 601479 (C4 (Web Text))

Max Activating Token Index: 623

Text #10

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.5472. Min Act: -0.0001

Data Index: 1198858 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.5740. Min Act: -0.0001

Data Index: 126500 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6499. Min Act: -0.0001

Data Index: 721199 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6286. Min Act: -0.0001

Data Index: 1091946 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6047. Min Act: -0.0001

Data Index: 330996 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6096. Min Act: -0.0001

Data Index: 721014 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6481. Min Act: -0.0001

Data Index: 1061429 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6032. Min Act: -0.0001

Data Index: 877410 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.5887. Min Act: -0.0001

Data Index: 259387 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.7321. Min Range: -0.7321

Max Act: 0.6067. Min Act: -0.0001

Data Index: 128339 (C4 (Web Text))

Max Activating Token Index: 883