Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2263 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.8195. Min Act: -0.0003

Data Index: 627015 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.7562. Min Act: -0.0003

Data Index: 436302 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.7097. Min Act: -0.0003

Data Index: 551424 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.7024. Min Act: -0.0003

Data Index: 397309 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6771. Min Act: -0.0003

Data Index: 30743 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.7208. Min Act: -0.0003

Data Index: 859929 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6380. Min Act: -0.0003

Data Index: 456670 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.7248. Min Act: -0.0003

Data Index: 735202 (C4 (Web Text))

Max Activating Token Index: 545

Text #8

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6996. Min Act: -0.0003

Data Index: 5514 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6667. Min Act: -0.0003

Data Index: 622769 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6670. Min Act: -0.0003

Data Index: 361210 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6746. Min Act: -0.0003

Data Index: 111361 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.7188. Min Act: -0.0003

Data Index: 61248 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6133. Min Act: -0.0003

Data Index: 1239758 (C4 (Web Text))

Max Activating Token Index: 563

Text #14

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6366. Min Act: -0.0003

Data Index: 1016125 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.7187. Min Act: -0.0003

Data Index: 931092 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6301. Min Act: -0.0003

Data Index: 453251 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.5864. Min Act: -0.0003

Data Index: 266105 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6808. Min Act: -0.0003

Data Index: 663593 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 0.8195. Min Range: -0.8195

Max Act: 0.6084. Min Act: -0.0003

Data Index: 872014 (C4 (Web Text))

Max Activating Token Index: 168