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

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

Neuron 1086 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: 1.1657. Min Range: -1.1657

Max Act: 1.1657. Min Act: -0.0000

Data Index: 1042470 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9817. Min Act: -0.0000

Data Index: 1337426 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9240. Min Act: -0.0000

Data Index: 903483 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8677. Min Act: -0.0000

Data Index: 1287604 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8369. Min Act: -0.0000

Data Index: 93474 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8605. Min Act: -0.0000

Data Index: 1528943 (Python Code)

Max Activating Token Index: 312

Text #6

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8526. Min Act: -0.0000

Data Index: 649899 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8488. Min Act: -0.0000

Data Index: 423048 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8394. Min Act: -0.0000

Data Index: 599213 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8083. Min Act: -0.0000

Data Index: 725098 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8358. Min Act: -0.0000

Data Index: 1212166 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1031825 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.7983. Min Act: -0.0000

Data Index: 332925 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.7840. Min Act: -0.0000

Data Index: 571931 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8019. Min Act: -0.0000

Data Index: 59344 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8017. Min Act: -0.0000

Data Index: 257334 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1518234 (Python Code)

Max Activating Token Index: 329

Text #17

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.7724. Min Act: -0.0000

Data Index: 137949 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.7362. Min Act: -0.0000

Data Index: 720774 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.7590. Min Act: -0.0000

Data Index: 1192702 (C4 (Web Text))

Max Activating Token Index: 33