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

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

Neuron 2398 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: 0.5144. Min Range: -0.5144

Max Act: 0.5144. Min Act: -0.0000

Data Index: 234562 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.4649. Min Act: -0.0000

Data Index: 856715 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.4443. Min Act: -0.0000

Data Index: 291442 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1354014 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.4236. Min Act: -0.0001

Data Index: 832338 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.4408. Min Act: -0.0000

Data Index: 1250598 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1174404 (C4 (Web Text))

Max Activating Token Index: 259

Text #7

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.4008. Min Act: -0.0000

Data Index: 426990 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.3975. Min Act: -0.0000

Data Index: 583477 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.4220. Min Act: -0.0000

Data Index: 995650 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1147543 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.4060. Min Act: -0.0000

Data Index: 922005 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.4046. Min Act: -0.0000

Data Index: 303957 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.3948. Min Act: -0.0000

Data Index: 655972 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.3708. Min Act: -0.0000

Data Index: 1326671 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.4109. Min Act: -0.0000

Data Index: 488252 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.3742. Min Act: -0.0000

Data Index: 1071740 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.3857. Min Act: -0.0000

Data Index: 286433 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.3952. Min Act: -0.0000

Data Index: 288739 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.5144. Min Range: -0.5144

Max Act: 0.3561. Min Act: -0.0000

Data Index: 21253 (C4 (Web Text))

Max Activating Token Index: 178