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

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

Neuron 5724 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: 3.6617. Min Range: -3.6617

Max Act: 3.6617. Min Act: -0.0000

Data Index: 148929 (C4 (Web Text))

Max Activating Token Index: 921

Text #1

Max Range: 3.6617. Min Range: -3.6617

Max Act: 3.0700. Min Act: -0.0000

Data Index: 1263760 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.9449. Min Act: -0.0000

Data Index: 888294 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.7757. Min Act: -0.0000

Data Index: 765921 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.7476. Min Act: -0.0000

Data Index: 313358 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.6242. Min Act: -0.0000

Data Index: 17558 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.5870. Min Act: -0.0000

Data Index: 160686 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.5290. Min Act: -0.0000

Data Index: 1116966 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.3464. Min Act: -0.0000

Data Index: 1193373 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.4165. Min Act: -0.0000

Data Index: 893063 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.3839. Min Act: -0.0000

Data Index: 1282769 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.3544. Min Act: -0.0000

Data Index: 1335273 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.3653. Min Act: -0.0000

Data Index: 375170 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.4749. Min Act: -0.0000

Data Index: 1217813 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.2550. Min Act: -0.0000

Data Index: 92712 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.3596. Min Act: -0.0000

Data Index: 1197589 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.2258. Min Act: -0.0000

Data Index: 468625 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.2261. Min Act: -0.0000

Data Index: 456433 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.3384. Min Act: -0.0000

Data Index: 1027066 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 3.6617. Min Range: -3.6617

Max Act: 2.2066. Min Act: -0.0000

Data Index: 273850 (C4 (Web Text))

Max Activating Token Index: 260