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

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

Neuron 2721 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.3049. Min Act: -0.0001

Data Index: 327728 (C4 (Web Text))

Max Activating Token Index: 191

Text #1

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.3474. Min Act: -0.0001

Data Index: 853706 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.2728. Min Act: -0.0001

Data Index: 1443322 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.2273. Min Act: -0.0001

Data Index: 891897 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.2908. Min Act: -0.0001

Data Index: 1158565 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.1498. Min Act: -0.0001

Data Index: 215301 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.2259. Min Act: -0.0001

Data Index: 1163487 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.2079. Min Act: -0.0001

Data Index: 159663 (C4 (Web Text))

Max Activating Token Index: 391

Text #8

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.1352. Min Act: -0.0001

Data Index: 995487 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.2053. Min Act: -0.0001

Data Index: 43635 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.1384. Min Act: -0.0001

Data Index: 1127478 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.1377. Min Act: -0.0001

Data Index: 1016332 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.1988. Min Act: -0.0001

Data Index: 360860 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.0812. Min Act: -0.0001

Data Index: 1631169 (Python Code)

Max Activating Token Index: 780

Text #14

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.0717. Min Act: -0.0001

Data Index: 1615115 (Python Code)

Max Activating Token Index: 608

Text #15

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.1691. Min Act: -0.0001

Data Index: 121024 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.2046. Min Act: -0.0001

Data Index: 342736 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.0638. Min Act: -0.0001

Data Index: 1167509 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.1223. Min Act: -0.0001

Data Index: 1166115 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 1.3474. Min Range: -1.3474

Max Act: 1.1169. Min Act: -0.0001

Data Index: 108795 (C4 (Web Text))

Max Activating Token Index: 115