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

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

Neuron 891 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.9156. Min Act: -0.0000

Data Index: 16542 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 3.0435. Min Range: -3.0435

Max Act: 3.0435. Min Act: -0.0000

Data Index: 272108 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.8378. Min Act: -0.0000

Data Index: 275734 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.9596. Min Act: -0.0000

Data Index: 306316 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.6874. Min Act: -0.0000

Data Index: 1104999 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.7874. Min Act: -0.0000

Data Index: 511034 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.7574. Min Act: -0.0000

Data Index: 535990 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.6123. Min Act: -0.0000

Data Index: 440070 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.7323. Min Act: -0.0000

Data Index: 181158 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.5577. Min Act: -0.0000

Data Index: 1273260 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.3862. Min Act: -0.0000

Data Index: 496218 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.7643. Min Act: -0.0000

Data Index: 981352 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.4832. Min Act: -0.0000

Data Index: 959460 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.5648. Min Act: -0.0000

Data Index: 1211666 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.6999. Min Act: -0.0000

Data Index: 861851 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.5354. Min Act: -0.0000

Data Index: 465460 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.5293. Min Act: -0.0000

Data Index: 1102784 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.6033. Min Act: -0.0000

Data Index: 909621 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.4556. Min Act: -0.0000

Data Index: 1117919 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 3.0435. Min Range: -3.0435

Max Act: 2.5911. Min Act: -0.0000

Data Index: 303009 (C4 (Web Text))

Max Activating Token Index: 234