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

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

Neuron 693 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.6175. Min Act: 0.0000

Data Index: 1436941 (Python Code)

Max Activating Token Index: 293

Text #1

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.3857. Min Act: -0.0000

Data Index: 182141 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.3932. Min Act: -0.0000

Data Index: 912080 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.3528. Min Act: -0.0000

Data Index: 24086 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1504909 (Python Code)

Max Activating Token Index: 248

Text #5

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.2793. Min Act: -0.0000

Data Index: 1447081 (Python Code)

Max Activating Token Index: 146

Text #6

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.3369. Min Act: -0.0000

Data Index: 874664 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1387828 (Python Code)

Max Activating Token Index: 317

Text #8

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.2707. Min Act: -0.0000

Data Index: 95946 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1374478 (Python Code)

Max Activating Token Index: 409

Text #10

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.2761. Min Act: 0.0000

Data Index: 1545664 (Python Code)

Max Activating Token Index: 867

Text #11

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1472432 (Python Code)

Max Activating Token Index: 653

Text #12

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.2892. Min Act: -0.0000

Data Index: 1499964 (Python Code)

Max Activating Token Index: 175

Text #13

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.2745. Min Act: -0.0000

Data Index: 1607196 (Python Code)

Max Activating Token Index: 743

Text #14

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1491901 (Python Code)

Max Activating Token Index: 187

Text #15

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1466761 (Python Code)

Max Activating Token Index: 935

Text #16

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1629300 (Python Code)

Max Activating Token Index: 326

Text #17

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.2451. Min Act: -0.0000

Data Index: 1537087 (Python Code)

Max Activating Token Index: 960

Text #18

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1363567 (Python Code)

Max Activating Token Index: 912

Text #19

Max Range: 0.6175. Min Range: -0.6175

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1385720 (Python Code)

Max Activating Token Index: 262