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

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

Neuron 441 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.7304. Min Act: -0.0000

Data Index: 335761 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.9244. Min Act: -0.0000

Data Index: 275107 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.6211. Min Act: -0.0000

Data Index: 384490 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.6873. Min Act: -0.0000

Data Index: 430627 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.5578. Min Act: -0.0000

Data Index: 655130 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.5235. Min Act: -0.0000

Data Index: 484700 (C4 (Web Text))

Max Activating Token Index: 268

Text #6

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.4791. Min Act: -0.0000

Data Index: 1082911 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.4203. Min Act: -0.0000

Data Index: 81004 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.4450. Min Act: -0.0000

Data Index: 568588 (C4 (Web Text))

Max Activating Token Index: 873

Text #9

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.4385. Min Act: -0.0000

Data Index: 121325 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.4363. Min Act: -0.0000

Data Index: 405941 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.3775. Min Act: -0.0001

Data Index: 1073792 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.3173. Min Act: -0.0000

Data Index: 1172161 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.3499. Min Act: -0.0000

Data Index: 557628 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.3242. Min Act: -0.0000

Data Index: 316458 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.1217. Min Act: -0.0000

Data Index: 1067718 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.2288. Min Act: -0.0000

Data Index: 522702 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.2917. Min Act: -0.0000

Data Index: 169964 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.2159. Min Act: -0.0001

Data Index: 1335649 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 1.9244. Min Range: -1.9244

Max Act: 1.1915. Min Act: -0.0000

Data Index: 1220756 (C4 (Web Text))

Max Activating Token Index: 114