Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5049 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.8247. Min Act: -0.0000

Data Index: 1218331 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.4811. Min Act: -0.0000

Data Index: 128356 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.1943. Min Act: -0.0001

Data Index: 896812 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.1987. Min Act: -0.0000

Data Index: 311418 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.1912. Min Act: -0.0000

Data Index: 1217193 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.0913. Min Act: -0.0000

Data Index: 216267 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.2622. Min Act: -0.0000

Data Index: 912160 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.2348. Min Act: -0.0000

Data Index: 809642 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.3373. Min Act: -0.0001

Data Index: 32909 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.0860. Min Act: -0.0000

Data Index: 1158414 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 2.8247. Min Range: -2.8247

Max Act: 1.7700. Min Act: -0.0001

Data Index: 564556 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.0656. Min Act: -0.0001

Data Index: 275351 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.1715. Min Act: -0.0000

Data Index: 1164130 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.1125. Min Act: -0.0000

Data Index: 160342 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.1991. Min Act: -0.0001

Data Index: 98898 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 2.8247. Min Range: -2.8247

Max Act: 1.9603. Min Act: -0.0000

Data Index: 940899 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 2.8247. Min Range: -2.8247

Max Act: 1.9521. Min Act: -0.0000

Data Index: 885078 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.1747. Min Act: -0.0000

Data Index: 434753 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 2.8247. Min Range: -2.8247

Max Act: 1.9536. Min Act: -0.0001

Data Index: 783146 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 2.8247. Min Range: -2.8247

Max Act: 2.0780. Min Act: -0.0000

Data Index: 821762 (C4 (Web Text))

Max Activating Token Index: 21