Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1251 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0723. Min Act: -0.0003

Data Index: 306861 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0699. Min Act: -0.0003

Data Index: 1271692 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0694. Min Act: -0.0003

Data Index: 144949 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0697. Min Act: -0.0003

Data Index: 98830 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0670. Min Act: -0.0003

Data Index: 226080 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0653. Min Act: -0.0003

Data Index: 165457 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0660. Min Act: -0.0003

Data Index: 1112614 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0641. Min Act: -0.0003

Data Index: 1284317 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0636. Min Act: -0.0004

Data Index: 141777 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0655. Min Act: -0.0003

Data Index: 1008700 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0656. Min Act: -0.0004

Data Index: 250876 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1157435 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0646. Min Act: -0.0003

Data Index: 1053434 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0638. Min Act: -0.0003

Data Index: 1311494 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0624. Min Act: -0.0003

Data Index: 422935 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1027233 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0637. Min Act: -0.0003

Data Index: 147423 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0622. Min Act: -0.0003

Data Index: 15654 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0625. Min Act: -0.0003

Data Index: 1110843 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.0723. Min Range: -0.0723

Max Act: 0.0633. Min Act: -0.0003

Data Index: 722107 (C4 (Web Text))

Max Activating Token Index: 676