Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2925 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.4830. Min Range: -6.4830

Max Act: 6.4830. Min Act: -0.0000

Data Index: 88422 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 6.4830. Min Range: -6.4830

Max Act: 6.0148. Min Act: -0.0000

Data Index: 1230036 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.8885. Min Act: -0.0000

Data Index: 97234 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.6943. Min Act: -0.0000

Data Index: 464861 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.6624. Min Act: -0.0000

Data Index: 1145051 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.6719. Min Act: -0.0000

Data Index: 36922 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.6450. Min Act: -0.0000

Data Index: 1066375 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.8300. Min Act: -0.0000

Data Index: 711667 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.6225. Min Act: -0.0000

Data Index: 233278 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.7929. Min Act: -0.0000

Data Index: 227705 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.5579. Min Act: -0.0000

Data Index: 86016 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.5346. Min Act: -0.0000

Data Index: 22128 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.6411. Min Act: -0.0000

Data Index: 1026941 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.6226. Min Act: -0.0000

Data Index: 98050 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.4065. Min Act: -0.0000

Data Index: 694981 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.3885. Min Act: -0.0000

Data Index: 670905 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.5094. Min Act: -0.0000

Data Index: 167610 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.5150. Min Act: -0.0000

Data Index: 503135 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.5054. Min Act: -0.0000

Data Index: 815432 (C4 (Web Text))

Max Activating Token Index: 518

Text #19

Max Range: 6.4830. Min Range: -6.4830

Max Act: 5.4887. Min Act: -0.0000

Data Index: 1351126 (C4 (Web Text))

Max Activating Token Index: 774