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

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

Neuron 44 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: 0.1611. Min Range: -0.1611

Max Act: 0.1611. Min Act: -0.0001

Data Index: 430575 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1449. Min Act: -0.0001

Data Index: 891326 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1327. Min Act: -0.0001

Data Index: 971119 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1291. Min Act: -0.0001

Data Index: 867406 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1186. Min Act: -0.0001

Data Index: 957214 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1008590 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1199. Min Act: -0.0001

Data Index: 1060479 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1240. Min Act: -0.0001

Data Index: 889128 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1167. Min Act: -0.0001

Data Index: 288087 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1123. Min Act: -0.0001

Data Index: 1027527 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1093. Min Act: -0.0001

Data Index: 610352 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1155456 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1121. Min Act: -0.0001

Data Index: 253465 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1122. Min Act: -0.0001

Data Index: 135921 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1099. Min Act: -0.0001

Data Index: 1243557 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1081. Min Act: -0.0001

Data Index: 505823 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1072. Min Act: -0.0001

Data Index: 222814 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1076. Min Act: -0.0001

Data Index: 797580 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1033. Min Act: -0.0001

Data Index: 184989 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.1611. Min Range: -0.1611

Max Act: 0.1074. Min Act: -0.0001

Data Index: 1327163 (C4 (Web Text))

Max Activating Token Index: 712