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

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

Neuron 3271 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.9016. Min Act: -0.0001

Data Index: 1445344 (Python Code)

Max Activating Token Index: 195

Text #1

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.5547. Min Act: -0.0001

Data Index: 1532302 (Python Code)

Max Activating Token Index: 771

Text #2

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.4171. Min Act: -0.0001

Data Index: 1590849 (Python Code)

Max Activating Token Index: 721

Text #3

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.4841. Min Act: -0.0001

Data Index: 1435751 (Python Code)

Max Activating Token Index: 274

Text #4

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.3874. Min Act: -0.0001

Data Index: 1122028 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.4039. Min Act: -0.0001

Data Index: 1640201 (Python Code)

Max Activating Token Index: 185

Text #6

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.2899. Min Act: -0.0001

Data Index: 1361268 (Python Code)

Max Activating Token Index: 620

Text #7

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.2872. Min Act: -0.0001

Data Index: 1144660 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.2421. Min Act: -0.0001

Data Index: 1616393 (Python Code)

Max Activating Token Index: 185

Text #9

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.2227. Min Act: -0.0001

Data Index: 1577065 (Python Code)

Max Activating Token Index: 247

Text #10

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.1541. Min Act: -0.0001

Data Index: 1627057 (Python Code)

Max Activating Token Index: 1015

Text #11

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.1867. Min Act: -0.0001

Data Index: 32895 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.0872. Min Act: -0.0001

Data Index: 1394771 (Python Code)

Max Activating Token Index: 420

Text #13

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.0565. Min Act: -0.0000

Data Index: 468813 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.0725. Min Act: -0.0001

Data Index: 744492 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.1031. Min Act: -0.0001

Data Index: 715821 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.1436. Min Act: -0.0001

Data Index: 621654 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.0315. Min Act: -0.0001

Data Index: 92862 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.0535. Min Act: -0.0001

Data Index: 51925 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 1.9016. Min Range: -1.9016

Max Act: 1.0755. Min Act: -0.0001

Data Index: 41790 (C4 (Web Text))

Max Activating Token Index: 858