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

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

Neuron 1280 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: 2.8060. Min Range: -2.8060

Max Act: 2.8060. Min Act: -0.0000

Data Index: 773574 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 2.8060. Min Range: -2.8060

Max Act: 2.6289. Min Act: -0.0001

Data Index: 217903 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 2.8060. Min Range: -2.8060

Max Act: 2.5778. Min Act: -0.0001

Data Index: 284542 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 2.8060. Min Range: -2.8060

Max Act: 2.3402. Min Act: -0.0001

Data Index: 1205938 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 2.8060. Min Range: -2.8060

Max Act: 2.5512. Min Act: -0.0000

Data Index: 99308 (C4 (Web Text))

Max Activating Token Index: 771

Text #5

Max Range: 2.8060. Min Range: -2.8060

Max Act: 2.4881. Min Act: -0.0001

Data Index: 1282730 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 2.8060. Min Range: -2.8060

Max Act: 2.0112. Min Act: -0.0001

Data Index: 296362 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 2.8060. Min Range: -2.8060

Max Act: 2.1985. Min Act: -0.0000

Data Index: 516319 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 2.8060. Min Range: -2.8060

Max Act: 2.2284. Min Act: -0.0001

Data Index: 870281 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 2.8060. Min Range: -2.8060

Max Act: 2.3623. Min Act: -0.0000

Data Index: 384936 (C4 (Web Text))

Max Activating Token Index: 409

Text #10

Max Range: 2.8060. Min Range: -2.8060

Max Act: 1.9252. Min Act: -0.0000

Data Index: 482886 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 2.8060. Min Range: -2.8060

Max Act: 2.1368. Min Act: -0.0000

Data Index: 290051 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 2.8060. Min Range: -2.8060

Max Act: 2.1095. Min Act: -0.0000

Data Index: 1080219 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 2.8060. Min Range: -2.8060

Max Act: 1.9814. Min Act: -0.0000

Data Index: 469644 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 2.8060. Min Range: -2.8060

Max Act: 1.8796. Min Act: -0.0000

Data Index: 961247 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 2.8060. Min Range: -2.8060

Max Act: 1.7957. Min Act: -0.0001

Data Index: 615947 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 2.8060. Min Range: -2.8060

Max Act: 1.9634. Min Act: -0.0000

Data Index: 1218187 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 2.8060. Min Range: -2.8060

Max Act: 1.9845. Min Act: -0.0000

Data Index: 962825 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 2.8060. Min Range: -2.8060

Max Act: 1.9527. Min Act: -0.0000

Data Index: 813330 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 2.8060. Min Range: -2.8060

Max Act: 1.8406. Min Act: -0.0000

Data Index: 977121 (C4 (Web Text))

Max Activating Token Index: 31