Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2009 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0518. Min Act: -0.0002

Data Index: 374801 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0517. Min Act: -0.0002

Data Index: 490435 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0544. Min Act: -0.0002

Data Index: 797911 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0482. Min Act: -0.0002

Data Index: 937777 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0480. Min Act: -0.0002

Data Index: 1457142 (Python Code)

Max Activating Token Index: 185

Text #5

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0444. Min Act: -0.0002

Data Index: 174976 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0422. Min Act: -0.0002

Data Index: 651004 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1148097 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0441. Min Act: -0.0002

Data Index: 626856 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0443. Min Act: -0.0002

Data Index: 65545 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1007219 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0449. Min Act: -0.0002

Data Index: 791195 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1188403 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1209458 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0437. Min Act: -0.0002

Data Index: 841477 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0407. Min Act: -0.0002

Data Index: 750359 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0404. Min Act: -0.0002

Data Index: 524165 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0395. Min Act: -0.0002

Data Index: 104435 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0409. Min Act: -0.0002

Data Index: 918161 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.0544. Min Range: -0.0544

Max Act: 0.0466. Min Act: -0.0002

Data Index: 158892 (C4 (Web Text))

Max Activating Token Index: 865