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

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

Neuron 4320 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: 0.9210. Min Range: -0.9210

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1320079 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.6777. Min Act: -0.0000

Data Index: 165425 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.6148. Min Act: -0.0000

Data Index: 733288 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.6542. Min Act: -0.0000

Data Index: 233140 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1353058 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.5927. Min Act: -0.0000

Data Index: 984974 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1105452 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.6027. Min Act: -0.0000

Data Index: 431923 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.6078. Min Act: -0.0000

Data Index: 557136 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.5412. Min Act: -0.0000

Data Index: 298976 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.5432. Min Act: -0.0000

Data Index: 116280 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.5935. Min Act: -0.0000

Data Index: 412684 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.5346. Min Act: -0.0000

Data Index: 478351 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.4886. Min Act: -0.0000

Data Index: 518726 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1203622 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.4924. Min Act: -0.0000

Data Index: 862358 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1277364 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1204344 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.5219. Min Act: -0.0000

Data Index: 170334 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.9210. Min Range: -0.9210

Max Act: 0.5168. Min Act: -0.0000

Data Index: 635979 (C4 (Web Text))

Max Activating Token Index: 730