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

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

Neuron 489 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0924. Min Act: -0.0002

Data Index: 16693 (C4 (Web Text))

Max Activating Token Index: 755

Text #1

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1105. Min Act: -0.0002

Data Index: 82469 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1218347 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1159658 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0797. Min Act: -0.0002

Data Index: 293362 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0873. Min Act: -0.0002

Data Index: 1188521 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1227686 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1115766 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0763. Min Act: -0.0002

Data Index: 759852 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1054742 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0764. Min Act: -0.0002

Data Index: 494228 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0709. Min Act: -0.0002

Data Index: 378214 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1344218 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0647. Min Act: -0.0002

Data Index: 837346 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0671. Min Act: -0.0002

Data Index: 943225 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0685. Min Act: -0.0002

Data Index: 38 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0717. Min Act: -0.0002

Data Index: 298268 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0714. Min Act: -0.0002

Data Index: 245213 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0701. Min Act: -0.0002

Data Index: 15049 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1071069 (C4 (Web Text))

Max Activating Token Index: 639