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

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

Neuron 2067 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.4999. Min Act: -0.0001

Data Index: 600957 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.4724. Min Act: -0.0001

Data Index: 1006186 (C4 (Web Text))

Max Activating Token Index: 719

Text #2

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.6057. Min Act: -0.0001

Data Index: 1246913 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.3977. Min Act: -0.0001

Data Index: 758800 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.3536. Min Act: -0.0001

Data Index: 1306982 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.3889. Min Act: -0.0001

Data Index: 1217143 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.3462. Min Act: -0.0001

Data Index: 1271487 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.3112. Min Act: -0.0001

Data Index: 410454 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.3061. Min Act: -0.0001

Data Index: 1337206 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.1775. Min Act: -0.0001

Data Index: 1089233 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.2054. Min Act: -0.0001

Data Index: 956935 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.1967. Min Act: -0.0001

Data Index: 1169738 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.2137. Min Act: -0.0001

Data Index: 769821 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.1684. Min Act: -0.0001

Data Index: 295662 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.1355. Min Act: -0.0001

Data Index: 1334160 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 1.6057. Min Range: -1.6057

Max Act: 0.9855. Min Act: -0.0001

Data Index: 61304 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.1249. Min Act: -0.0001

Data Index: 746409 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.1121. Min Act: -0.0001

Data Index: 1195765 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.0601. Min Act: -0.0001

Data Index: 351083 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 1.6057. Min Range: -1.6057

Max Act: 1.0169. Min Act: -0.0001

Data Index: 433666 (C4 (Web Text))

Max Activating Token Index: 728