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

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

Neuron 4345 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0736. Min Act: -0.0002

Data Index: 738763 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0739. Min Act: -0.0002

Data Index: 399259 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0673. Min Act: -0.0002

Data Index: 703808 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1004597 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0571. Min Act: -0.0002

Data Index: 187890 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0639. Min Act: -0.0002

Data Index: 606589 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1618115 (Python Code)

Max Activating Token Index: 231

Text #7

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0561. Min Act: -0.0002

Data Index: 635033 (C4 (Web Text))

Max Activating Token Index: 505

Text #8

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0664. Min Act: -0.0002

Data Index: 879627 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0546. Min Act: -0.0002

Data Index: 411723 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0507. Min Act: -0.0002

Data Index: 419260 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0544. Min Act: -0.0002

Data Index: 441362 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1172252 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1420257 (Python Code)

Max Activating Token Index: 788

Text #14

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0520. Min Act: -0.0002

Data Index: 69118 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1356320 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0459. Min Act: -0.0002

Data Index: 374438 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0524. Min Act: -0.0002

Data Index: 844051 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1630697 (Python Code)

Max Activating Token Index: 576

Text #19

Max Range: 0.0739. Min Range: -0.0739

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1029308 (C4 (Web Text))

Max Activating Token Index: 709