Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 588 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1328983 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4429. Min Act: -0.0000

Data Index: 996865 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3935. Min Act: -0.0000

Data Index: 628486 (C4 (Web Text))

Max Activating Token Index: 390

Text #3

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3836. Min Act: -0.0000

Data Index: 479266 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3387. Min Act: -0.0000

Data Index: 253841 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3566. Min Act: -0.0000

Data Index: 1078542 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3548. Min Act: -0.0000

Data Index: 1320888 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.4148. Min Act: -0.0000

Data Index: 212429 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3350. Min Act: 0.0000

Data Index: 209687 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3335. Min Act: -0.0000

Data Index: 319214 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3076. Min Act: 0.0000

Data Index: 42673 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1189731 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1247468 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3044. Min Act: -0.0000

Data Index: 971711 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.2396. Min Act: -0.0000

Data Index: 672229 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3223. Min Act: -0.0000

Data Index: 1015912 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3007. Min Act: 0.0000

Data Index: 1149986 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3180. Min Act: -0.0000

Data Index: 789593 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.3165. Min Act: -0.0000

Data Index: 59053 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.5462. Min Range: -0.5462

Max Act: 0.2958. Min Act: -0.0000

Data Index: 571548 (C4 (Web Text))

Max Activating Token Index: 392