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

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

Neuron 1054 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: 4.8742. Min Range: -4.8742

Max Act: 4.8742. Min Act: -0.0000

Data Index: 1054082 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.9272. Min Act: -0.0000

Data Index: 499676 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.6227. Min Act: -0.0000

Data Index: 169666 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.7661. Min Act: -0.0000

Data Index: 1309214 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.4043. Min Act: -0.0000

Data Index: 439811 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.5798. Min Act: -0.0001

Data Index: 992348 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.3536. Min Act: -0.0000

Data Index: 1261892 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.6607. Min Act: -0.0000

Data Index: 575174 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.4987. Min Act: -0.0000

Data Index: 835249 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.3299. Min Act: -0.0000

Data Index: 1025680 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.4039. Min Act: -0.0001

Data Index: 1337733 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.3555. Min Act: -0.0000

Data Index: 1195986 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.4566. Min Act: -0.0000

Data Index: 970073 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.2803. Min Act: -0.0000

Data Index: 884351 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.1462. Min Act: -0.0000

Data Index: 174018 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.2118. Min Act: -0.0000

Data Index: 615156 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.3594. Min Act: -0.0000

Data Index: 116733 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.0562. Min Act: -0.0000

Data Index: 920167 (C4 (Web Text))

Max Activating Token Index: 379

Text #18

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.0300. Min Act: -0.0000

Data Index: 752156 (C4 (Web Text))

Max Activating Token Index: 716

Text #19

Max Range: 4.8742. Min Range: -4.8742

Max Act: 3.1456. Min Act: -0.0000

Data Index: 207562 (C4 (Web Text))

Max Activating Token Index: 401