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

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

Neuron 877 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: 1.2094. Min Range: -1.2094

Max Act: 1.2094. Min Act: -0.0000

Data Index: 762508 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.1318. Min Act: -0.0000

Data Index: 1010397 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.1262. Min Act: -0.0000

Data Index: 385725 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.0522. Min Act: -0.0000

Data Index: 788018 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.0171. Min Act: -0.0000

Data Index: 456265 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 1.2094. Min Range: -1.2094

Max Act: 1.0152. Min Act: -0.0000

Data Index: 263201 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8943. Min Act: -0.0000

Data Index: 1058441 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8621. Min Act: -0.0000

Data Index: 552564 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8561. Min Act: -0.0000

Data Index: 24462 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8445. Min Act: -0.0000

Data Index: 330239 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8417. Min Act: -0.0000

Data Index: 988001 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8020. Min Act: -0.0000

Data Index: 95231 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8462. Min Act: -0.0000

Data Index: 1161277 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.7851. Min Act: -0.0000

Data Index: 1352383 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8228. Min Act: -0.0000

Data Index: 1483930 (Python Code)

Max Activating Token Index: 435

Text #15

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8133. Min Act: -0.0000

Data Index: 996509 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1178201 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8144. Min Act: -0.0000

Data Index: 315221 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.8214. Min Act: -0.0000

Data Index: 554166 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 1.2094. Min Range: -1.2094

Max Act: 0.7378. Min Act: -0.0000

Data Index: 600844 (C4 (Web Text))

Max Activating Token Index: 1022