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

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

Neuron 3699 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: 0.8036. Min Range: -0.8036

Max Act: 0.8036. Min Act: 0.0002

Data Index: 340916 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6801. Min Act: -0.0000

Data Index: 142268 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.7093. Min Act: -0.0001

Data Index: 25085 (C4 (Web Text))

Max Activating Token Index: 832

Text #3

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.7009. Min Act: -0.0001

Data Index: 1321703 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6995. Min Act: -0.0000

Data Index: 1316630 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1351550 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6701. Min Act: -0.0000

Data Index: 681192 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6716. Min Act: 0.0003

Data Index: 772451 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6802. Min Act: -0.0000

Data Index: 146842 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6757. Min Act: -0.0001

Data Index: 849631 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6434. Min Act: -0.0000

Data Index: 879251 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6246. Min Act: -0.0001

Data Index: 1337381 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5927. Min Act: -0.0001

Data Index: 749873 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6065. Min Act: 0.0000

Data Index: 948224 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5973. Min Act: -0.0000

Data Index: 948360 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6241. Min Act: -0.0001

Data Index: 337164 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5802. Min Act: -0.0001

Data Index: 119141 (C4 (Web Text))

Max Activating Token Index: 966

Text #17

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.6132. Min Act: -0.0000

Data Index: 970145 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1311259 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.8036. Min Range: -0.8036

Max Act: 0.5911. Min Act: -0.0000

Data Index: 97861 (C4 (Web Text))

Max Activating Token Index: 968