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

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

Neuron 1272 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.7048. Min Act: -0.0000

Data Index: 530920 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.6952. Min Act: -0.0000

Data Index: 310149 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1095804 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.6980. Min Act: -0.0000

Data Index: 825434 (C4 (Web Text))

Max Activating Token Index: 230

Text #4

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.6198. Min Act: -0.0000

Data Index: 652643 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.6748. Min Act: -0.0000

Data Index: 178154 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.6042. Min Act: -0.0000

Data Index: 261644 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5545. Min Act: -0.0000

Data Index: 879044 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5315. Min Act: -0.0000

Data Index: 536384 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5258. Min Act: -0.0000

Data Index: 1044293 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1287843 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5171. Min Act: -0.0000

Data Index: 350082 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.5069. Min Act: -0.0000

Data Index: 481794 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4827. Min Act: -0.0000

Data Index: 90692 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4837. Min Act: -0.0000

Data Index: 99093 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4678. Min Act: -0.0000

Data Index: 82867 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4806. Min Act: -0.0000

Data Index: 233030 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4737. Min Act: -0.0000

Data Index: 868898 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1104920 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.7048. Min Range: -0.7048

Max Act: 0.4982. Min Act: -0.0000

Data Index: 621126 (C4 (Web Text))

Max Activating Token Index: 727