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

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

Neuron 826 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: 2.4158. Min Range: -2.4158

Max Act: 2.3763. Min Act: -0.0000

Data Index: 254305 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.3067. Min Act: -0.0000

Data Index: 31814 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.4158. Min Act: -0.0000

Data Index: 1079917 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.2683. Min Act: -0.0000

Data Index: 965753 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.4051. Min Act: -0.0000

Data Index: 248086 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.2694. Min Act: -0.0000

Data Index: 1242670 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.3317. Min Act: -0.0000

Data Index: 610527 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.3749. Min Act: -0.0000

Data Index: 898597 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.1166. Min Act: -0.0000

Data Index: 1323713 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.1541. Min Act: -0.0000

Data Index: 499591 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.2001. Min Act: -0.0000

Data Index: 1138649 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.2050. Min Act: -0.0000

Data Index: 699372 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.1366. Min Act: -0.0000

Data Index: 298771 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.3181. Min Act: -0.0000

Data Index: 723729 (C4 (Web Text))

Max Activating Token Index: 637

Text #14

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.2569. Min Act: -0.0000

Data Index: 861016 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.1667. Min Act: -0.0000

Data Index: 118377 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.2877. Min Act: -0.0000

Data Index: 84640 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.0164. Min Act: -0.0000

Data Index: 285318 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.0670. Min Act: -0.0000

Data Index: 9135 (C4 (Web Text))

Max Activating Token Index: 712

Text #19

Max Range: 2.4158. Min Range: -2.4158

Max Act: 2.1647. Min Act: -0.0000

Data Index: 628345 (C4 (Web Text))

Max Activating Token Index: 417