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

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

Neuron 4531 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2872. Min Act: -0.0000

Data Index: 97626 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2779. Min Act: -0.0000

Data Index: 330203 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2492. Min Act: -0.0000

Data Index: 816808 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1637715 (Python Code)

Max Activating Token Index: 674

Text #4

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2186. Min Act: -0.0000

Data Index: 83802 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1011503 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2079. Min Act: -0.0000

Data Index: 560544 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1460687 (Python Code)

Max Activating Token Index: 553

Text #8

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2159. Min Act: -0.0000

Data Index: 127234 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1641768 (Python Code)

Max Activating Token Index: 194

Text #10

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2070. Min Act: -0.0000

Data Index: 1536653 (Python Code)

Max Activating Token Index: 75

Text #11

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2094. Min Act: -0.0000

Data Index: 1589825 (Python Code)

Max Activating Token Index: 555

Text #12

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1223672 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1442153 (Python Code)

Max Activating Token Index: 907

Text #14

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1656369 (Python Code)

Max Activating Token Index: 453

Text #15

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1510642 (Python Code)

Max Activating Token Index: 243

Text #16

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1610558 (Python Code)

Max Activating Token Index: 797

Text #17

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2040. Min Act: -0.0000

Data Index: 402004 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1498827 (Python Code)

Max Activating Token Index: 115

Text #19

Max Range: 0.2872. Min Range: -0.2872

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1493681 (Python Code)

Max Activating Token Index: 411