Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 60 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0533. Min Act: -0.0000

Data Index: 1340223 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0507. Min Act: -0.0000

Data Index: 271472 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0490. Min Act: -0.0001

Data Index: 954206 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0501. Min Act: -0.0000

Data Index: 741941 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0552. Min Act: -0.0000

Data Index: 489948 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0459. Min Act: -0.0000

Data Index: 155778 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0510. Min Act: -0.0000

Data Index: 1350365 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0461. Min Act: -0.0000

Data Index: 1559612 (Python Code)

Max Activating Token Index: 233

Text #8

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0448. Min Act: -0.0001

Data Index: 324267 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0447. Min Act: -0.0000

Data Index: 924207 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0420. Min Act: -0.0000

Data Index: 1019565 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0506. Min Act: -0.0000

Data Index: 754024 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0468. Min Act: -0.0000

Data Index: 658336 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0434. Min Act: -0.0000

Data Index: 1250684 (C4 (Web Text))

Max Activating Token Index: 797

Text #14

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0403. Min Act: -0.0001

Data Index: 120224 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0445. Min Act: -0.0000

Data Index: 309245 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0411. Min Act: -0.0000

Data Index: 1238057 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0423. Min Act: -0.0000

Data Index: 558788 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0420. Min Act: -0.0000

Data Index: 843241 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.0552. Min Range: -0.0552

Max Act: 0.0432. Min Act: -0.0001

Data Index: 948449 (C4 (Web Text))

Max Activating Token Index: 851