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

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

Neuron 3703 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8171. Min Act: -0.0001

Data Index: 1172546 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.9096. Min Act: -0.0001

Data Index: 738519 (C4 (Web Text))

Max Activating Token Index: 263

Text #2

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8037. Min Act: -0.0001

Data Index: 249457 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7777. Min Act: -0.0001

Data Index: 774374 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8154. Min Act: -0.0001

Data Index: 460547 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7792. Min Act: -0.0001

Data Index: 290523 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8422. Min Act: -0.0001

Data Index: 154999 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7751. Min Act: -0.0001

Data Index: 175950 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7521. Min Act: -0.0001

Data Index: 164606 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.8060. Min Act: -0.0001

Data Index: 406747 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7971. Min Act: -0.0001

Data Index: 578056 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7783. Min Act: -0.0001

Data Index: 731853 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7723. Min Act: -0.0001

Data Index: 284290 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7444. Min Act: -0.0001

Data Index: 326954 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7391. Min Act: -0.0001

Data Index: 66504 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7457. Min Act: -0.0000

Data Index: 1002715 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7445. Min Act: -0.0001

Data Index: 953941 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7434. Min Act: -0.0001

Data Index: 741281 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7701. Min Act: -0.0001

Data Index: 120620 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.9096. Min Range: -0.9096

Max Act: 0.7782. Min Act: -0.0001

Data Index: 1354929 (C4 (Web Text))

Max Activating Token Index: 930