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

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

Neuron 2074 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: 0.6212. Min Range: -0.6212

Max Act: 0.6064. Min Act: -0.0003

Data Index: 864577 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.6212. Min Act: -0.0003

Data Index: 1175195 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5673. Min Act: -0.0003

Data Index: 409401 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5477. Min Act: -0.0003

Data Index: 1119458 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5522. Min Act: -0.0003

Data Index: 95959 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5558. Min Act: -0.0003

Data Index: 670397 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4996. Min Act: -0.0003

Data Index: 920973 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5310. Min Act: -0.0003

Data Index: 106288 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5414. Min Act: -0.0003

Data Index: 973178 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5371. Min Act: -0.0003

Data Index: 342940 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.4788. Min Act: -0.0003

Data Index: 1121820 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5282. Min Act: -0.0003

Data Index: 1300686 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5302. Min Act: -0.0003

Data Index: 1197084 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5305. Min Act: -0.0003

Data Index: 981873 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5658. Min Act: -0.0003

Data Index: 1150339 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5554. Min Act: -0.0003

Data Index: 1174139 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5040. Min Act: -0.0003

Data Index: 692329 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5500. Min Act: -0.0003

Data Index: 1034244 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5032. Min Act: -0.0003

Data Index: 1152464 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.6212. Min Range: -0.6212

Max Act: 0.5045. Min Act: -0.0003

Data Index: 672508 (C4 (Web Text))

Max Activating Token Index: 667