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

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

Neuron 1003 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5014. Min Range: -3.5014

Max Act: 3.5014. Min Act: -0.0000

Data Index: 1164757 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.9695. Min Act: -0.0000

Data Index: 637214 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.7738. Min Act: -0.0000

Data Index: 589007 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 3.5014. Min Range: -3.5014

Max Act: 3.1576. Min Act: -0.0000

Data Index: 1207820 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 3.5014. Min Range: -3.5014

Max Act: 3.2103. Min Act: -0.0000

Data Index: 1326776 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.8834. Min Act: -0.0000

Data Index: 2671 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 3.5014. Min Range: -3.5014

Max Act: 3.0142. Min Act: -0.0000

Data Index: 170995 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.7926. Min Act: -0.0000

Data Index: 776055 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.7331. Min Act: -0.0000

Data Index: 668514 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.6812. Min Act: -0.0000

Data Index: 759836 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.5026. Min Act: -0.0000

Data Index: 448609 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.6356. Min Act: -0.0000

Data Index: 603118 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.4746. Min Act: -0.0000

Data Index: 984150 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.5851. Min Act: -0.0000

Data Index: 1418695 (Python Code)

Max Activating Token Index: 826

Text #14

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.4426. Min Act: -0.0000

Data Index: 1424537 (Python Code)

Max Activating Token Index: 832

Text #15

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.5367. Min Act: -0.0000

Data Index: 1449559 (Python Code)

Max Activating Token Index: 71

Text #16

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.5392. Min Act: -0.0000

Data Index: 1546398 (Python Code)

Max Activating Token Index: 880

Text #17

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.5546. Min Act: -0.0000

Data Index: 1323278 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.5595. Min Act: -0.0000

Data Index: 1528935 (Python Code)

Max Activating Token Index: 154

Text #19

Max Range: 3.5014. Min Range: -3.5014

Max Act: 2.6830. Min Act: -0.0000

Data Index: 1545255 (Python Code)

Max Activating Token Index: 61