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

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

Neuron 5523 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0420. Min Range: -1.0420

Max Act: 1.0420. Min Act: -0.0000

Data Index: 281656 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.8900. Min Act: -0.0000

Data Index: 632637 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.8434. Min Act: -0.0000

Data Index: 954609 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7384. Min Act: -0.0000

Data Index: 427897 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.9063. Min Act: -0.0000

Data Index: 106753 (C4 (Web Text))

Max Activating Token Index: 417

Text #5

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.8912. Min Act: -0.0000

Data Index: 283083 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7610. Min Act: -0.0000

Data Index: 78162 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.8319. Min Act: -0.0000

Data Index: 1333259 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1104184 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7138. Min Act: -0.0000

Data Index: 799787 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1280936 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7776. Min Act: -0.0000

Data Index: 415747 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7529. Min Act: -0.0000

Data Index: 493461 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7501. Min Act: -0.0000

Data Index: 2541 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7054. Min Act: -0.0000

Data Index: 962177 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7947. Min Act: -0.0000

Data Index: 576553 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1088207 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1181945 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7364. Min Act: -0.0000

Data Index: 1106460 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7398. Min Act: -0.0000

Data Index: 797559 (C4 (Web Text))

Max Activating Token Index: 173