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

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

Neuron 351 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3351. Min Range: -1.3351

Max Act: 1.3351. Min Act: -0.0001

Data Index: 315196 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 1.3351. Min Range: -1.3351

Max Act: 1.1715. Min Act: -0.0000

Data Index: 232990 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 1.3351. Min Range: -1.3351

Max Act: 1.1691. Min Act: -0.0001

Data Index: 180436 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.4572. Min Act: -0.0000

Data Index: 216490 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.5356. Min Act: -0.0001

Data Index: 1184663 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.4328. Min Act: -0.0001

Data Index: 114103 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.3915. Min Act: -0.0001

Data Index: 322230 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.4004. Min Act: -0.0000

Data Index: 753485 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.4080. Min Act: -0.0001

Data Index: 837569 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.4684. Min Act: -0.0001

Data Index: 381174 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.3901. Min Act: -0.0001

Data Index: 995549 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.3314. Min Act: -0.0001

Data Index: 723846 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.3085. Min Act: -0.0001

Data Index: 441262 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.3213. Min Act: -0.0001

Data Index: 1181751 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.3706. Min Act: -0.0001

Data Index: 270693 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.2979. Min Act: -0.0001

Data Index: 754805 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.3023. Min Act: -0.0001

Data Index: 919158 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.2892. Min Act: -0.0001

Data Index: 631937 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.2526. Min Act: -0.0001

Data Index: 1064700 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 1.3351. Min Range: -1.3351

Max Act: 0.2847. Min Act: -0.0001

Data Index: 1071311 (C4 (Web Text))

Max Activating Token Index: 987