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

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

Neuron 80 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: 1.3312. Min Range: -1.3312

Max Act: 1.3312. Min Act: -0.0000

Data Index: 619252 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.3312. Min Range: -1.3312

Max Act: 1.2730. Min Act: -0.0000

Data Index: 945706 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 1.3312. Min Range: -1.3312

Max Act: 1.1942. Min Act: -0.0000

Data Index: 489660 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 1.3312. Min Range: -1.3312

Max Act: 1.2072. Min Act: -0.0001

Data Index: 1259343 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 1.3312. Min Range: -1.3312

Max Act: 1.1542. Min Act: -0.0000

Data Index: 1272101 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 1.3312. Min Range: -1.3312

Max Act: 1.1431. Min Act: -0.0000

Data Index: 1252994 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 1.3312. Min Range: -1.3312

Max Act: 1.0068. Min Act: -0.0000

Data Index: 490920 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 1.3312. Min Range: -1.3312

Max Act: 1.0794. Min Act: -0.0000

Data Index: 896481 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 1.3312. Min Range: -1.3312

Max Act: 1.0531. Min Act: -0.0000

Data Index: 395700 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 1.3312. Min Range: -1.3312

Max Act: 0.9937. Min Act: -0.0001

Data Index: 1243053 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 1.3312. Min Range: -1.3312

Max Act: 0.9829. Min Act: -0.0001

Data Index: 405482 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 1.3312. Min Range: -1.3312

Max Act: 1.0896. Min Act: -0.0000

Data Index: 510943 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 1.3312. Min Range: -1.3312

Max Act: 1.0753. Min Act: -0.0001

Data Index: 1208351 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 1.3312. Min Range: -1.3312

Max Act: 0.9375. Min Act: -0.0000

Data Index: 1234351 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 1.3312. Min Range: -1.3312

Max Act: 0.9528. Min Act: -0.0000

Data Index: 712887 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 1.3312. Min Range: -1.3312

Max Act: 0.9361. Min Act: -0.0000

Data Index: 391622 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 1.3312. Min Range: -1.3312

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1181255 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 1.3312. Min Range: -1.3312

Max Act: 0.9313. Min Act: -0.0000

Data Index: 1283821 (C4 (Web Text))

Max Activating Token Index: 298

Text #18

Max Range: 1.3312. Min Range: -1.3312

Max Act: 1.0205. Min Act: -0.0000

Data Index: 180257 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 1.3312. Min Range: -1.3312

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1117690 (C4 (Web Text))

Max Activating Token Index: 909