Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4167 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.9711. Min Range: -3.9711

Max Act: 3.9711. Min Act: 0.0000

Data Index: 878936 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 3.9711. Min Range: -3.9711

Max Act: 2.9987. Min Act: -0.0000

Data Index: 1261277 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 3.9711. Min Range: -3.9711

Max Act: 3.0727. Min Act: -0.0000

Data Index: 76854 (C4 (Web Text))

Max Activating Token Index: 519

Text #3

Max Range: 3.9711. Min Range: -3.9711

Max Act: 3.0151. Min Act: -0.0000

Data Index: 923940 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 3.9711. Min Range: -3.9711

Max Act: 3.0077. Min Act: -0.0000

Data Index: 1286407 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 3.9711. Min Range: -3.9711

Max Act: 3.2902. Min Act: 0.0000

Data Index: 806148 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 3.9711. Min Range: -3.9711

Max Act: 2.9658. Min Act: -0.0000

Data Index: 1157539 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 3.9711. Min Range: -3.9711

Max Act: 2.7084. Min Act: 0.0000

Data Index: 196158 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 3.9711. Min Range: -3.9711

Max Act: 2.8512. Min Act: -0.0000

Data Index: 378737 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 3.9711. Min Range: -3.9711

Max Act: 2.6282. Min Act: 0.0000

Data Index: 994592 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 3.9711. Min Range: -3.9711

Max Act: 2.6959. Min Act: -0.0000

Data Index: 852381 (C4 (Web Text))

Max Activating Token Index: 917

Text #11

Max Range: 3.9711. Min Range: -3.9711

Max Act: 2.7907. Min Act: -0.0000

Data Index: 931058 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 3.9711. Min Range: -3.9711

Max Act: 2.7523. Min Act: -0.0000

Data Index: 1280167 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 3.9711. Min Range: -3.9711

Max Act: 1.8369. Min Act: -0.0000

Data Index: 49919 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 3.9711. Min Range: -3.9711

Max Act: 2.5566. Min Act: -0.0000

Data Index: 655762 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 3.9711. Min Range: -3.9711

Max Act: 2.3647. Min Act: -0.0000

Data Index: 679521 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 3.9711. Min Range: -3.9711

Max Act: 2.4789. Min Act: -0.0000

Data Index: 764094 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 3.9711. Min Range: -3.9711

Max Act: 2.2390. Min Act: -0.0000

Data Index: 1160574 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 3.9711. Min Range: -3.9711

Max Act: 2.4242. Min Act: -0.0000

Data Index: 398104 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 3.9711. Min Range: -3.9711

Max Act: 2.3751. Min Act: -0.0000

Data Index: 674704 (C4 (Web Text))

Max Activating Token Index: 434