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

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

Neuron 1995 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: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0002

Data Index: 421983 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0477. Min Act: -0.0002

Data Index: 1307889 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1501167 (Python Code)

Max Activating Token Index: 95

Text #3

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0443. Min Act: -0.0002

Data Index: 517279 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0470. Min Act: -0.0002

Data Index: 825943 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0466. Min Act: -0.0002

Data Index: 1634422 (Python Code)

Max Activating Token Index: 97

Text #6

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1504656 (Python Code)

Max Activating Token Index: 858

Text #7

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0458. Min Act: -0.0002

Data Index: 1503880 (Python Code)

Max Activating Token Index: 184

Text #8

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0449. Min Act: -0.0002

Data Index: 71620 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1521999 (Python Code)

Max Activating Token Index: 790

Text #10

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0453. Min Act: -0.0002

Data Index: 428131 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1604055 (Python Code)

Max Activating Token Index: 37

Text #12

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0426. Min Act: -0.0001

Data Index: 1500313 (Python Code)

Max Activating Token Index: 445

Text #13

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0434. Min Act: -0.0002

Data Index: 802016 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0398. Min Act: -0.0002

Data Index: 361712 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0417. Min Act: -0.0002

Data Index: 1516293 (Python Code)

Max Activating Token Index: 453

Text #16

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0443. Min Act: -0.0002

Data Index: 636082 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0446. Min Act: -0.0002

Data Index: 395208 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0421. Min Act: -0.0000

Data Index: 218088 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0400. Min Act: -0.0002

Data Index: 90891 (C4 (Web Text))

Max Activating Token Index: 471