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

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

Neuron 320 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8647. Min Act: -0.0001

Data Index: 899442 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.9739. Min Act: -0.0001

Data Index: 1059428 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.9099. Min Act: -0.0001

Data Index: 861864 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.9027. Min Act: -0.0001

Data Index: 114095 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.9559. Min Act: -0.0001

Data Index: 323995 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.7645. Min Act: -0.0001

Data Index: 1080652 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8298. Min Act: -0.0001

Data Index: 89536 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.9354. Min Act: -0.0001

Data Index: 176641 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8438. Min Act: -0.0001

Data Index: 1130076 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.7846. Min Act: -0.0001

Data Index: 237682 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8142. Min Act: -0.0001

Data Index: 912718 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8617. Min Act: -0.0001

Data Index: 1427689 (Python Code)

Max Activating Token Index: 471

Text #12

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8117. Min Act: -0.0001

Data Index: 961783 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8084. Min Act: -0.0001

Data Index: 1416042 (Python Code)

Max Activating Token Index: 53

Text #14

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.6701. Min Act: -0.0001

Data Index: 879138 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8328. Min Act: -0.0001

Data Index: 657416 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8306. Min Act: -0.0001

Data Index: 1276794 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.7677. Min Act: -0.0001

Data Index: 1515193 (Python Code)

Max Activating Token Index: 116

Text #18

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.7508. Min Act: -0.0001

Data Index: 144911 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8092. Min Act: -0.0001

Data Index: 989633 (C4 (Web Text))

Max Activating Token Index: 231