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

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

Neuron 2330 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0157. Min Range: -3.0157

Max Act: 3.0157. Min Act: -0.0000

Data Index: 459916 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.7469. Min Act: -0.0000

Data Index: 430404 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.6770. Min Act: -0.0000

Data Index: 662372 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.6283. Min Act: -0.0000

Data Index: 384129 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.7241. Min Act: -0.0000

Data Index: 612734 (C4 (Web Text))

Max Activating Token Index: 235

Text #5

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.5753. Min Act: -0.0000

Data Index: 378567 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.4954. Min Act: -0.0000

Data Index: 18552 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.3704. Min Act: -0.0000

Data Index: 120316 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.2858. Min Act: -0.0000

Data Index: 1292987 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.1631. Min Act: -0.0000

Data Index: 843568 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.2721. Min Act: -0.0000

Data Index: 283424 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.2666. Min Act: -0.0000

Data Index: 504538 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.3482. Min Act: -0.0000

Data Index: 806079 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.1703. Min Act: -0.0000

Data Index: 338432 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.2400. Min Act: -0.0000

Data Index: 639996 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.1233. Min Act: -0.0000

Data Index: 65662 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.1149. Min Act: -0.0000

Data Index: 1322474 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.1127. Min Act: -0.0000

Data Index: 533180 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.1032. Min Act: -0.0000

Data Index: 156709 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 3.0157. Min Range: -3.0157

Max Act: 2.0947. Min Act: -0.0000

Data Index: 1206574 (C4 (Web Text))

Max Activating Token Index: 216