Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2275 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1228. Min Act: -0.0001

Data Index: 395425 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1580. Min Act: -0.0001

Data Index: 1307355 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1184. Min Act: -0.0001

Data Index: 228575 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1140. Min Act: -0.0001

Data Index: 129313 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1088. Min Act: -0.0001

Data Index: 1216460 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1296. Min Act: -0.0001

Data Index: 866537 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1217. Min Act: -0.0001

Data Index: 196776 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1161. Min Act: -0.0001

Data Index: 474364 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1000. Min Act: -0.0001

Data Index: 116086 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1114. Min Act: -0.0001

Data Index: 479463 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1068. Min Act: -0.0001

Data Index: 273101 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0984. Min Act: -0.0001

Data Index: 2657 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1121. Min Act: -0.0001

Data Index: 460225 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1120. Min Act: -0.0001

Data Index: 1012521 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1141. Min Act: -0.0001

Data Index: 281932 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0803. Min Act: -0.0001

Data Index: 985174 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0983. Min Act: -0.0001

Data Index: 342268 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1050. Min Act: -0.0001

Data Index: 482157 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.1082. Min Act: -0.0001

Data Index: 99446 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 0.1580. Min Range: -0.1580

Max Act: 0.0929. Min Act: -0.0001

Data Index: 105668 (C4 (Web Text))

Max Activating Token Index: 778