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

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

Neuron 4331 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4000. Min Range: -4.4000

Max Act: 4.2315. Min Act: -0.0000

Data Index: 1007321 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 4.4000. Min Range: -4.4000

Max Act: 4.1597. Min Act: -0.0000

Data Index: 124796 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 4.4000. Min Range: -4.4000

Max Act: 4.2741. Min Act: -0.0000

Data Index: 210269 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 4.4000. Min Range: -4.4000

Max Act: 4.2248. Min Act: -0.0000

Data Index: 171685 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 4.4000. Min Range: -4.4000

Max Act: 4.4000. Min Act: -0.0000

Data Index: 64533 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 4.4000. Min Range: -4.4000

Max Act: 4.1305. Min Act: -0.0000

Data Index: 1045615 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 4.4000. Min Range: -4.4000

Max Act: 4.3483. Min Act: -0.0000

Data Index: 1236161 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 4.4000. Min Range: -4.4000

Max Act: 4.0692. Min Act: -0.0000

Data Index: 1074273 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 4.4000. Min Range: -4.4000

Max Act: 4.0008. Min Act: -0.0000

Data Index: 883489 (C4 (Web Text))

Max Activating Token Index: 628

Text #9

Max Range: 4.4000. Min Range: -4.4000

Max Act: 3.8048. Min Act: -0.0000

Data Index: 1290480 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 4.4000. Min Range: -4.4000

Max Act: 3.7747. Min Act: -0.0000

Data Index: 421193 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 4.4000. Min Range: -4.4000

Max Act: 3.6208. Min Act: -0.0000

Data Index: 815618 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 4.4000. Min Range: -4.4000

Max Act: 3.7269. Min Act: -0.0000

Data Index: 250575 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 4.4000. Min Range: -4.4000

Max Act: 3.7324. Min Act: -0.0000

Data Index: 1040475 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 4.4000. Min Range: -4.4000

Max Act: 3.7068. Min Act: -0.0000

Data Index: 544311 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 4.4000. Min Range: -4.4000

Max Act: 3.6846. Min Act: -0.0000

Data Index: 814175 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 4.4000. Min Range: -4.4000

Max Act: 3.7658. Min Act: -0.0000

Data Index: 1109840 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 4.4000. Min Range: -4.4000

Max Act: 3.5759. Min Act: -0.0000

Data Index: 560463 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 4.4000. Min Range: -4.4000

Max Act: 3.5690. Min Act: -0.0000

Data Index: 923767 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 4.4000. Min Range: -4.4000

Max Act: 3.5612. Min Act: -0.0000

Data Index: 281946 (C4 (Web Text))

Max Activating Token Index: 125