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

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

Neuron 3076 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: 2.7922. Min Range: -2.7922

Max Act: 2.7922. Min Act: -0.0000

Data Index: 1183696 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.6818. Min Act: -0.0000

Data Index: 237968 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.1659. Min Act: -0.0000

Data Index: 856003 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.3829. Min Act: -0.0000

Data Index: 752571 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.4919. Min Act: -0.0000

Data Index: 910890 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.4538. Min Act: -0.0000

Data Index: 1333985 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.1931. Min Act: -0.0000

Data Index: 703389 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.3090. Min Act: -0.0000

Data Index: 393637 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.2948. Min Act: -0.0000

Data Index: 836706 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.2419. Min Act: -0.0000

Data Index: 942312 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.3607. Min Act: -0.0000

Data Index: 1196748 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.2662. Min Act: -0.0000

Data Index: 16364 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.1289. Min Act: -0.0000

Data Index: 291335 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.1263. Min Act: -0.0000

Data Index: 827759 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.1069. Min Act: -0.0000

Data Index: 595339 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 2.7922. Min Range: -2.7922

Max Act: 1.9618. Min Act: -0.0000

Data Index: 996139 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.0491. Min Act: -0.0000

Data Index: 621967 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 2.7922. Min Range: -2.7922

Max Act: 2.1629. Min Act: -0.0000

Data Index: 167620 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 2.7922. Min Range: -2.7922

Max Act: 1.8135. Min Act: -0.0000

Data Index: 984566 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 2.7922. Min Range: -2.7922

Max Act: 1.9080. Min Act: -0.0000

Data Index: 478755 (C4 (Web Text))

Max Activating Token Index: 350