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

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

Neuron 564 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2824. Min Act: -0.0002

Data Index: 1511206 (Python Code)

Max Activating Token Index: 889

Text #1

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2761. Min Act: -0.0002

Data Index: 1498316 (Python Code)

Max Activating Token Index: 960

Text #2

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2683. Min Act: -0.0002

Data Index: 1581316 (Python Code)

Max Activating Token Index: 938

Text #3

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2591. Min Act: -0.0002

Data Index: 577347 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2630. Min Act: -0.0002

Data Index: 149163 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2587. Min Act: -0.0002

Data Index: 1326154 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2521. Min Act: -0.0002

Data Index: 1363116 (Python Code)

Max Activating Token Index: 1008

Text #7

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2414. Min Act: -0.0002

Data Index: 1471615 (Python Code)

Max Activating Token Index: 791

Text #8

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2392. Min Act: -0.0002

Data Index: 1553180 (Python Code)

Max Activating Token Index: 232

Text #9

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2448. Min Act: -0.0002

Data Index: 826599 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2250. Min Act: -0.0002

Data Index: 120234 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2308. Min Act: -0.0002

Data Index: 973401 (C4 (Web Text))

Max Activating Token Index: 454

Text #12

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2119. Min Act: -0.0002

Data Index: 1360077 (Python Code)

Max Activating Token Index: 734

Text #13

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2131. Min Act: -0.0002

Data Index: 316471 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2102. Min Act: -0.0002

Data Index: 1289544 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2166. Min Act: -0.0002

Data Index: 107397 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1927. Min Act: -0.0002

Data Index: 720186 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.2008. Min Act: -0.0002

Data Index: 871741 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1972. Min Act: -0.0002

Data Index: 1187365 (C4 (Web Text))

Max Activating Token Index: 935

Text #19

Max Range: 0.2824. Min Range: -0.2824

Max Act: 0.1884. Min Act: -0.0002

Data Index: 1043752 (C4 (Web Text))

Max Activating Token Index: 339