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

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

Neuron 6129 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: 3.2841. Min Range: -3.2841

Max Act: 3.2841. Min Act: -0.0000

Data Index: 1293676 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 3.2841. Min Range: -3.2841

Max Act: 3.2371. Min Act: -0.0000

Data Index: 75345 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 3.2841. Min Range: -3.2841

Max Act: 2.7193. Min Act: -0.0000

Data Index: 1015768 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 3.2841. Min Range: -3.2841

Max Act: 2.6494. Min Act: -0.0000

Data Index: 84246 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 3.2841. Min Range: -3.2841

Max Act: 2.4440. Min Act: -0.0000

Data Index: 284314 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 3.2841. Min Range: -3.2841

Max Act: 2.2732. Min Act: -0.0000

Data Index: 1094625 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 3.2841. Min Range: -3.2841

Max Act: 2.4898. Min Act: -0.0000

Data Index: 871575 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 3.2841. Min Range: -3.2841

Max Act: 2.1946. Min Act: -0.0000

Data Index: 1160522 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 3.2841. Min Range: -3.2841

Max Act: 2.1857. Min Act: -0.0000

Data Index: 31363 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 3.2841. Min Range: -3.2841

Max Act: 2.2926. Min Act: -0.0000

Data Index: 496109 (C4 (Web Text))

Max Activating Token Index: 406

Text #10

Max Range: 3.2841. Min Range: -3.2841

Max Act: 2.2329. Min Act: -0.0000

Data Index: 667275 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 3.2841. Min Range: -3.2841

Max Act: 2.2098. Min Act: -0.0000

Data Index: 831303 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 3.2841. Min Range: -3.2841

Max Act: 2.2906. Min Act: -0.0000

Data Index: 775163 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 3.2841. Min Range: -3.2841

Max Act: 2.1526. Min Act: -0.0000

Data Index: 669044 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 3.2841. Min Range: -3.2841

Max Act: 1.8875. Min Act: -0.0000

Data Index: 254204 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 3.2841. Min Range: -3.2841

Max Act: 1.9376. Min Act: -0.0000

Data Index: 674227 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 3.2841. Min Range: -3.2841

Max Act: 1.9119. Min Act: -0.0000

Data Index: 799989 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 3.2841. Min Range: -3.2841

Max Act: 1.9049. Min Act: -0.0000

Data Index: 706756 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 3.2841. Min Range: -3.2841

Max Act: 2.1099. Min Act: -0.0000

Data Index: 1321325 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 3.2841. Min Range: -3.2841

Max Act: 2.0539. Min Act: -0.0000

Data Index: 1246408 (C4 (Web Text))

Max Activating Token Index: 946