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

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

Neuron 6116 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4531. Min Range: -2.4531

Max Act: 2.4531. Min Act: -0.0000

Data Index: 217281 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 2.4531. Min Range: -2.4531

Max Act: 2.3293. Min Act: -0.0000

Data Index: 1264434 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 2.4531. Min Range: -2.4531

Max Act: 2.2336. Min Act: -0.0000

Data Index: 515821 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 2.4531. Min Range: -2.4531

Max Act: 2.3326. Min Act: -0.0000

Data Index: 129591 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 2.4531. Min Range: -2.4531

Max Act: 2.0238. Min Act: -0.0000

Data Index: 1555424 (Python Code)

Max Activating Token Index: 675

Text #5

Max Range: 2.4531. Min Range: -2.4531

Max Act: 2.0119. Min Act: -0.0000

Data Index: 822547 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 2.4531. Min Range: -2.4531

Max Act: 1.9218. Min Act: 0.0000

Data Index: 293223 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 2.4531. Min Range: -2.4531

Max Act: 1.8647. Min Act: -0.0000

Data Index: 708148 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 2.4531. Min Range: -2.4531

Max Act: 1.9173. Min Act: -0.0000

Data Index: 480866 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 2.4531. Min Range: -2.4531

Max Act: 1.6939. Min Act: -0.0000

Data Index: 836137 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 2.4531. Min Range: -2.4531

Max Act: 1.6557. Min Act: -0.0000

Data Index: 1007138 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 2.4531. Min Range: -2.4531

Max Act: 1.7580. Min Act: -0.0000

Data Index: 269461 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 2.4531. Min Range: -2.4531

Max Act: 1.7486. Min Act: -0.0000

Data Index: 1240484 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 2.4531. Min Range: -2.4531

Max Act: 1.7275. Min Act: -0.0000

Data Index: 992124 (C4 (Web Text))

Max Activating Token Index: 866

Text #14

Max Range: 2.4531. Min Range: -2.4531

Max Act: 1.7190. Min Act: -0.0000

Data Index: 1335882 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 2.4531. Min Range: -2.4531

Max Act: 1.7076. Min Act: -0.0000

Data Index: 1460712 (Python Code)

Max Activating Token Index: 989

Text #16

Max Range: 2.4531. Min Range: -2.4531

Max Act: 1.6584. Min Act: -0.0000

Data Index: 504049 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 2.4531. Min Range: -2.4531

Max Act: 1.5515. Min Act: -0.0000

Data Index: 758266 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 2.4531. Min Range: -2.4531

Max Act: 1.6020. Min Act: -0.0000

Data Index: 161398 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 2.4531. Min Range: -2.4531

Max Act: 1.7066. Min Act: -0.0000

Data Index: 306223 (C4 (Web Text))

Max Activating Token Index: 15