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

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

Neuron 4638 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5202. Min Range: -4.5202

Max Act: 4.5202. Min Act: -0.0000

Data Index: 141256 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 4.5202. Min Range: -4.5202

Max Act: 4.0858. Min Act: -0.0000

Data Index: 1539636 (Python Code)

Max Activating Token Index: 1021

Text #2

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.6922. Min Act: -0.0000

Data Index: 1090646 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.7101. Min Act: -0.0000

Data Index: 1325883 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.6702. Min Act: -0.0000

Data Index: 320848 (C4 (Web Text))

Max Activating Token Index: 986

Text #5

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.5462. Min Act: -0.0000

Data Index: 601956 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.3179. Min Act: -0.0000

Data Index: 1168122 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.2680. Min Act: -0.0000

Data Index: 864569 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.1144. Min Act: -0.0000

Data Index: 1491171 (Python Code)

Max Activating Token Index: 712

Text #9

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.3778. Min Act: -0.0000

Data Index: 1594344 (Python Code)

Max Activating Token Index: 93

Text #10

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.2392. Min Act: -0.0000

Data Index: 1557167 (Python Code)

Max Activating Token Index: 663

Text #11

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.3668. Min Act: -0.0000

Data Index: 1486317 (Python Code)

Max Activating Token Index: 15

Text #12

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.4210. Min Act: -0.0000

Data Index: 1258251 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.2266. Min Act: -0.0000

Data Index: 749270 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.2012. Min Act: -0.0000

Data Index: 1559027 (Python Code)

Max Activating Token Index: 663

Text #15

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.1770. Min Act: -0.0000

Data Index: 835447 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 4.5202. Min Range: -4.5202

Max Act: 2.8836. Min Act: -0.0000

Data Index: 1565891 (Python Code)

Max Activating Token Index: 912

Text #17

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.0211. Min Act: -0.0000

Data Index: 1394118 (Python Code)

Max Activating Token Index: 906

Text #18

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.1017. Min Act: -0.0000

Data Index: 484187 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 4.5202. Min Range: -4.5202

Max Act: 3.1316. Min Act: -0.0000

Data Index: 273060 (C4 (Web Text))

Max Activating Token Index: 26