Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 873 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3052. Min Act: -0.0001

Data Index: 1438378 (Python Code)

Max Activating Token Index: 881

Text #1

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3673. Min Act: -0.0001

Data Index: 682078 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3362. Min Act: -0.0001

Data Index: 1503096 (Python Code)

Max Activating Token Index: 997

Text #3

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3217. Min Act: -0.0001

Data Index: 1612145 (Python Code)

Max Activating Token Index: 826

Text #4

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3155. Min Act: -0.0001

Data Index: 382656 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3344. Min Act: -0.0001

Data Index: 1100453 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3211. Min Act: -0.0001

Data Index: 1592113 (Python Code)

Max Activating Token Index: 1007

Text #7

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3308. Min Act: -0.0001

Data Index: 212873 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3432. Min Act: -0.0001

Data Index: 780709 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3091. Min Act: -0.0001

Data Index: 1598897 (Python Code)

Max Activating Token Index: 794

Text #10

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3336. Min Act: -0.0001

Data Index: 1523236 (Python Code)

Max Activating Token Index: 663

Text #11

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3245. Min Act: -0.0001

Data Index: 1093417 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3145. Min Act: -0.0001

Data Index: 1632973 (Python Code)

Max Activating Token Index: 975

Text #13

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3261. Min Act: -0.0001

Data Index: 658289 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3111. Min Act: -0.0001

Data Index: 1627437 (Python Code)

Max Activating Token Index: 994

Text #15

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3098. Min Act: -0.0001

Data Index: 1458572 (Python Code)

Max Activating Token Index: 754

Text #16

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3211. Min Act: -0.0001

Data Index: 1515547 (Python Code)

Max Activating Token Index: 635

Text #17

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3331. Min Act: -0.0001

Data Index: 420279 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.3392. Min Act: -0.0001

Data Index: 1445341 (Python Code)

Max Activating Token Index: 786

Text #19

Max Range: 0.3673. Min Range: -0.3673

Max Act: 0.2951. Min Act: -0.0001

Data Index: 1475481 (Python Code)

Max Activating Token Index: 929