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

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

Neuron 133 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: 1.6307. Min Range: -1.6307

Max Act: 1.6307. Min Act: -0.0002

Data Index: 412328 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.3854. Min Act: -0.0002

Data Index: 65772 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.3878. Min Act: -0.0002

Data Index: 277079 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.2490. Min Act: -0.0002

Data Index: 818537 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.1554. Min Act: -0.0002

Data Index: 432292 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.1732. Min Act: -0.0002

Data Index: 1083619 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.1178. Min Act: -0.0002

Data Index: 768283 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.2456. Min Act: -0.0002

Data Index: 101870 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.0646. Min Act: -0.0002

Data Index: 84078 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.1237. Min Act: -0.0002

Data Index: 111035 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.0096. Min Act: -0.0002

Data Index: 144053 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.0345. Min Act: -0.0002

Data Index: 713475 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.0316. Min Act: -0.0002

Data Index: 519101 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 1.6307. Min Range: -1.6307

Max Act: 0.8799. Min Act: -0.0002

Data Index: 171113 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.0089. Min Act: -0.0002

Data Index: 65380 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.0601. Min Act: -0.0002

Data Index: 997961 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.0301. Min Act: -0.0002

Data Index: 1133018 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 1.6307. Min Range: -1.6307

Max Act: 0.9967. Min Act: -0.0002

Data Index: 1238227 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.0321. Min Act: -0.0002

Data Index: 1036669 (C4 (Web Text))

Max Activating Token Index: 984

Text #19

Max Range: 1.6307. Min Range: -1.6307

Max Act: 1.0658. Min Act: -0.0002

Data Index: 719586 (C4 (Web Text))

Max Activating Token Index: 572