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

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

Neuron 3236 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8819. Min Act: -0.0001

Data Index: 576605 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.8089. Min Act: -0.0001

Data Index: 312715 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7599. Min Act: -0.0001

Data Index: 1277873 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7908. Min Act: -0.0001

Data Index: 453123 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6248. Min Act: -0.0001

Data Index: 1291040 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7422. Min Act: -0.0001

Data Index: 366853 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6990. Min Act: -0.0001

Data Index: 154571 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6968. Min Act: -0.0001

Data Index: 656630 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6931. Min Act: -0.0001

Data Index: 1176574 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6397. Min Act: -0.0001

Data Index: 1023756 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6947. Min Act: -0.0001

Data Index: 613279 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6905. Min Act: -0.0001

Data Index: 54082 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6316. Min Act: -0.0001

Data Index: 603651 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6817. Min Act: -0.0001

Data Index: 826498 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6010. Min Act: -0.0001

Data Index: 1032571 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6869. Min Act: -0.0001

Data Index: 1297266 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6037. Min Act: -0.0001

Data Index: 923619 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6459. Min Act: -0.0001

Data Index: 404245 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.7038. Min Act: -0.0001

Data Index: 137646 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.8819. Min Range: -0.8819

Max Act: 0.6369. Min Act: -0.0001

Data Index: 571557 (C4 (Web Text))

Max Activating Token Index: 508