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

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

Neuron 1732 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: 1.7143. Min Range: -1.7143

Max Act: 1.5622. Min Act: -0.0001

Data Index: 48544 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.6215. Min Act: -0.0001

Data Index: 704176 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.6132. Min Act: -0.0001

Data Index: 1185272 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.5971. Min Act: -0.0001

Data Index: 722645 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.5766. Min Act: -0.0001

Data Index: 626736 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.7143. Min Act: -0.0001

Data Index: 321898 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.4383. Min Act: -0.0001

Data Index: 687953 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.4438. Min Act: -0.0001

Data Index: 508330 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.4355. Min Act: -0.0001

Data Index: 1004864 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.2971. Min Act: -0.0001

Data Index: 399000 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.4068. Min Act: -0.0001

Data Index: 1169967 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.2561. Min Act: -0.0001

Data Index: 1120002 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.3834. Min Act: -0.0001

Data Index: 89126 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.2247. Min Act: -0.0001

Data Index: 747463 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.5381. Min Act: -0.0001

Data Index: 1308226 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.2885. Min Act: -0.0001

Data Index: 823210 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.2041. Min Act: -0.0001

Data Index: 1120634 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.2450. Min Act: -0.0001

Data Index: 961964 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.3044. Min Act: -0.0001

Data Index: 1056842 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 1.7143. Min Range: -1.7143

Max Act: 1.0470. Min Act: -0.0001

Data Index: 1054480 (C4 (Web Text))

Max Activating Token Index: 680