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

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

Neuron 265 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: 0.0653. Min Range: -0.0653

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1465195 (Python Code)

Max Activating Token Index: 95

Text #1

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0489. Min Act: -0.0002

Data Index: 475470 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0467. Min Act: -0.0002

Data Index: 1064104 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1505258 (Python Code)

Max Activating Token Index: 857

Text #4

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1425573 (Python Code)

Max Activating Token Index: 259

Text #5

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0460. Min Act: -0.0002

Data Index: 811445 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1576748 (Python Code)

Max Activating Token Index: 994

Text #7

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0452. Min Act: -0.0002

Data Index: 600818 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0428. Min Act: -0.0001

Data Index: 656479 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0449. Min Act: -0.0001

Data Index: 1018765 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1516593 (Python Code)

Max Activating Token Index: 87

Text #11

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1578478 (Python Code)

Max Activating Token Index: 668

Text #12

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0426. Min Act: -0.0001

Data Index: 1605507 (Python Code)

Max Activating Token Index: 712

Text #13

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1396918 (Python Code)

Max Activating Token Index: 130

Text #14

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0424. Min Act: -0.0002

Data Index: 152802 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1206451 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0425. Min Act: -0.0001

Data Index: 1633901 (Python Code)

Max Activating Token Index: 257

Text #17

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1364630 (Python Code)

Max Activating Token Index: 831

Text #18

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0442. Min Act: -0.0002

Data Index: 83009 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 0.0653. Min Range: -0.0653

Max Act: 0.0432. Min Act: -0.0001

Data Index: 1059153 (C4 (Web Text))

Max Activating Token Index: 682