Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1622 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0168. Min Act: -0.0005

Data Index: 592566 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0161. Min Act: -0.0005

Data Index: 758831 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0162. Min Act: -0.0005

Data Index: 1085876 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0153. Min Act: -0.0006

Data Index: 392210 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0155. Min Act: -0.0005

Data Index: 399104 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0148. Min Act: -0.0005

Data Index: 765702 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0143. Min Act: -0.0005

Data Index: 363782 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0145. Min Act: -0.0005

Data Index: 637734 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0145. Min Act: -0.0006

Data Index: 705809 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0140. Min Act: -0.0005

Data Index: 841892 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0139. Min Act: -0.0005

Data Index: 397132 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0135. Min Act: -0.0005

Data Index: 1274928 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0128. Min Act: -0.0005

Data Index: 676653 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0126. Min Act: -0.0005

Data Index: 663682 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0127. Min Act: -0.0005

Data Index: 671448 (C4 (Web Text))

Max Activating Token Index: 1007

Text #15

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0123. Min Act: -0.0005

Data Index: 728495 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0126. Min Act: -0.0005

Data Index: 1132632 (C4 (Web Text))

Max Activating Token Index: 438

Text #17

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0125. Min Act: -0.0005

Data Index: 462011 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0125. Min Act: -0.0005

Data Index: 803857 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.0168. Min Range: -0.0168

Max Act: 0.0121. Min Act: -0.0005

Data Index: 878921 (C4 (Web Text))

Max Activating Token Index: 530