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

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

Neuron 1192 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: 0.7763. Min Range: -0.7763

Max Act: 0.7763. Min Act: -0.0000

Data Index: 522271 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1031259 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.6641. Min Act: -0.0000

Data Index: 151885 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.6591. Min Act: -0.0000

Data Index: 323305 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.6695. Min Act: -0.0000

Data Index: 386783 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.6033. Min Act: -0.0000

Data Index: 856578 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.6076. Min Act: -0.0000

Data Index: 341887 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.5751. Min Act: -0.0000

Data Index: 958535 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.5824. Min Act: -0.0000

Data Index: 33389 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.5820. Min Act: -0.0000

Data Index: 341144 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.5349. Min Act: -0.0000

Data Index: 1289341 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.5825. Min Act: -0.0000

Data Index: 671381 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.6147. Min Act: -0.0000

Data Index: 236866 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.5743. Min Act: -0.0000

Data Index: 173737 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.5840. Min Act: -0.0000

Data Index: 376287 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.5440. Min Act: -0.0000

Data Index: 656192 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1065004 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.5458. Min Act: -0.0000

Data Index: 744970 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.5543. Min Act: -0.0000

Data Index: 1012861 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.7763. Min Range: -0.7763

Max Act: 0.5485. Min Act: -0.0000

Data Index: 474717 (C4 (Web Text))

Max Activating Token Index: 595