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

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

Neuron 685 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: 2.1208. Min Range: -2.1208

Max Act: 2.1208. Min Act: -0.0000

Data Index: 1251884 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.8376. Min Act: -0.0000

Data Index: 268225 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.9590. Min Act: -0.0000

Data Index: 106261 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.9415. Min Act: -0.0000

Data Index: 328754 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.9468. Min Act: -0.0000

Data Index: 531342 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.8338. Min Act: -0.0000

Data Index: 319782 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.9301. Min Act: -0.0000

Data Index: 223814 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.7047. Min Act: -0.0000

Data Index: 624961 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.7045. Min Act: -0.0000

Data Index: 1083316 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.7943. Min Act: -0.0000

Data Index: 754368 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.9162. Min Act: -0.0000

Data Index: 313215 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.6806. Min Act: -0.0000

Data Index: 58189 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.6560. Min Act: -0.0000

Data Index: 838794 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.8468. Min Act: -0.0000

Data Index: 41189 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.6432. Min Act: -0.0000

Data Index: 300127 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.5928. Min Act: -0.0000

Data Index: 343841 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.5674. Min Act: -0.0000

Data Index: 847077 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.5759. Min Act: -0.0000

Data Index: 900247 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.5667. Min Act: -0.0000

Data Index: 831799 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 2.1208. Min Range: -2.1208

Max Act: 1.5687. Min Act: -0.0000

Data Index: 45346 (C4 (Web Text))

Max Activating Token Index: 959