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

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

Neuron 1369 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: 0.1150. Min Range: -0.1150

Max Act: 0.1150. Min Act: -0.0002

Data Index: 1608233 (Python Code)

Max Activating Token Index: 142

Text #1

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1061. Min Act: -0.0002

Data Index: 917085 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1023969 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0851. Min Act: -0.0002

Data Index: 780161 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1380947 (Python Code)

Max Activating Token Index: 257

Text #5

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0860. Min Act: -0.0002

Data Index: 1530834 (Python Code)

Max Activating Token Index: 154

Text #6

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0908. Min Act: -0.0002

Data Index: 864307 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0853. Min Act: -0.0002

Data Index: 454365 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1509458 (Python Code)

Max Activating Token Index: 102

Text #9

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0760. Min Act: -0.0001

Data Index: 1499371 (Python Code)

Max Activating Token Index: 306

Text #10

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0887. Min Act: -0.0002

Data Index: 479089 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0886. Min Act: -0.0002

Data Index: 1236423 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1284259 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1570176 (Python Code)

Max Activating Token Index: 205

Text #14

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0917. Min Act: -0.0002

Data Index: 203947 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0816. Min Act: -0.0002

Data Index: 945146 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1002786 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1461614 (Python Code)

Max Activating Token Index: 805

Text #18

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0798. Min Act: -0.0002

Data Index: 1077707 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0796. Min Act: -0.0002

Data Index: 977389 (C4 (Web Text))

Max Activating Token Index: 523