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

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

Neuron 1398 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.5930. Min Act: -0.0002

Data Index: 11456 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.3432. Min Act: -0.0002

Data Index: 685873 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.2850. Min Act: -0.0002

Data Index: 453510 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.3315. Min Act: -0.0002

Data Index: 853360 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.2984. Min Act: -0.0002

Data Index: 1318085 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.3205. Min Act: -0.0002

Data Index: 718470 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.1926. Min Act: -0.0002

Data Index: 772932 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.2278. Min Act: -0.0002

Data Index: 1038350 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.1858. Min Act: -0.0002

Data Index: 1259011 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.0649. Min Act: -0.0002

Data Index: 197100 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.0649. Min Act: -0.0002

Data Index: 1154817 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.1468. Min Act: -0.0002

Data Index: 577057 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.1630. Min Act: -0.0002

Data Index: 194476 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.3109. Min Act: -0.0002

Data Index: 911688 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.0708. Min Act: -0.0002

Data Index: 797870 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 1.5930. Min Range: -1.5930

Max Act: 0.9995. Min Act: -0.0002

Data Index: 694259 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.1761. Min Act: -0.0002

Data Index: 1235642 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.0460. Min Act: -0.0002

Data Index: 381821 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 1.5930. Min Range: -1.5930

Max Act: 1.0686. Min Act: -0.0002

Data Index: 808282 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 1.5930. Min Range: -1.5930

Max Act: 0.9710. Min Act: -0.0002

Data Index: 260102 (C4 (Web Text))

Max Activating Token Index: 40