Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2868 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.7487. Min Act: -0.0001

Data Index: 708637 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.5096. Min Act: -0.0001

Data Index: 1106446 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.5359. Min Act: -0.0001

Data Index: 1101513 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.5306. Min Act: -0.0001

Data Index: 664256 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.5164. Min Act: -0.0001

Data Index: 880565 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.4411. Min Act: -0.0001

Data Index: 248631 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.4737. Min Act: -0.0001

Data Index: 691916 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.4793. Min Act: -0.0001

Data Index: 1301812 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.3945. Min Act: -0.0001

Data Index: 620378 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.3883. Min Act: -0.0001

Data Index: 796630 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.4124. Min Act: -0.0001

Data Index: 364334 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.4206. Min Act: -0.0001

Data Index: 680507 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.3947. Min Act: -0.0001

Data Index: 216214 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.2991. Min Act: -0.0001

Data Index: 1221615 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.3468. Min Act: -0.0001

Data Index: 517957 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.3728. Min Act: -0.0001

Data Index: 741059 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.2918. Min Act: -0.0001

Data Index: 550260 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.2320. Min Act: -0.0001

Data Index: 1172789 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.2364. Min Act: -0.0001

Data Index: 1239448 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 1.7487. Min Range: -1.7487

Max Act: 1.3110. Min Act: -0.0001

Data Index: 1111184 (C4 (Web Text))

Max Activating Token Index: 43