Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3631 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.3637. Min Act: -0.0001

Data Index: 706113 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.3126. Min Act: -0.0000

Data Index: 425628 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2963. Min Act: -0.0001

Data Index: 935662 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.3074. Min Act: -0.0001

Data Index: 1131685 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2901. Min Act: -0.0000

Data Index: 988703 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1012224 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2736. Min Act: -0.0001

Data Index: 1128004 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2583. Min Act: -0.0000

Data Index: 567520 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2613. Min Act: 0.0001

Data Index: 1547388 (Python Code)

Max Activating Token Index: 75

Text #9

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2522. Min Act: -0.0000

Data Index: 1069812 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2605. Min Act: -0.0000

Data Index: 1028265 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2607. Min Act: -0.0000

Data Index: 891717 (C4 (Web Text))

Max Activating Token Index: 836

Text #12

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2513. Min Act: -0.0000

Data Index: 1488179 (Python Code)

Max Activating Token Index: 880

Text #13

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2571. Min Act: -0.0001

Data Index: 829120 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2476. Min Act: -0.0000

Data Index: 43819 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2382. Min Act: -0.0000

Data Index: 968107 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2458. Min Act: -0.0000

Data Index: 271820 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2342. Min Act: 0.0001

Data Index: 1628837 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2279. Min Act: 0.0004

Data Index: 1620310 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2297. Min Act: -0.0000

Data Index: 1071840 (C4 (Web Text))

Max Activating Token Index: 39