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

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

Neuron 5252 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: 2.1630. Min Range: -2.1630

Max Act: 2.1630. Min Act: -0.0000

Data Index: 363625 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 2.1630. Min Range: -2.1630

Max Act: 2.0093. Min Act: -0.0000

Data Index: 194122 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 2.1630. Min Range: -2.1630

Max Act: 2.0061. Min Act: -0.0000

Data Index: 536890 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.8029. Min Act: -0.0000

Data Index: 354820 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.9626. Min Act: -0.0000

Data Index: 721277 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.9453. Min Act: -0.0000

Data Index: 933367 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.7426. Min Act: -0.0000

Data Index: 1194957 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.7233. Min Act: -0.0000

Data Index: 191221 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.7949. Min Act: -0.0000

Data Index: 1273515 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.6136. Min Act: -0.0000

Data Index: 1282041 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.8003. Min Act: -0.0000

Data Index: 239968 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.7995. Min Act: -0.0000

Data Index: 924424 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.5114. Min Act: -0.0000

Data Index: 1083034 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.8414. Min Act: -0.0000

Data Index: 154875 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.8495. Min Act: -0.0000

Data Index: 131236 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.6525. Min Act: -0.0000

Data Index: 3464 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.6361. Min Act: -0.0000

Data Index: 1342730 (C4 (Web Text))

Max Activating Token Index: 758

Text #17

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.7250. Min Act: -0.0000

Data Index: 539646 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.6244. Min Act: -0.0000

Data Index: 925903 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 2.1630. Min Range: -2.1630

Max Act: 1.7228. Min Act: -0.0000

Data Index: 171990 (C4 (Web Text))

Max Activating Token Index: 384