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

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

Neuron 3378 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3713. Min Act: -0.0003

Data Index: 1627184 (Python Code)

Max Activating Token Index: 72

Text #1

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.3244. Min Act: -0.0002

Data Index: 755781 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2982. Min Act: -0.0002

Data Index: 975390 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2692. Min Act: -0.0003

Data Index: 682745 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2464. Min Act: -0.0003

Data Index: 442423 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2226. Min Act: -0.0003

Data Index: 170841 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2217. Min Act: -0.0002

Data Index: 1320545 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2152. Min Act: -0.0002

Data Index: 838699 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2214. Min Act: -0.0003

Data Index: 1202478 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2009. Min Act: -0.0003

Data Index: 514820 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.2030. Min Act: -0.0002

Data Index: 435257 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1944. Min Act: -0.0003

Data Index: 1302345 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1986. Min Act: -0.0003

Data Index: 340035 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1930. Min Act: -0.0003

Data Index: 1070075 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1851. Min Act: -0.0002

Data Index: 204072 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1848. Min Act: -0.0003

Data Index: 775678 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1835. Min Act: -0.0002

Data Index: 1319002 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1732. Min Act: -0.0003

Data Index: 765035 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1729. Min Act: -0.0003

Data Index: 531848 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 0.3713. Min Range: -0.3713

Max Act: 0.1556. Min Act: -0.0003

Data Index: 1349992 (C4 (Web Text))

Max Activating Token Index: 878