Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1593 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.7548. Min Act: -0.0001

Data Index: 87953 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6815. Min Act: -0.0001

Data Index: 908176 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6789. Min Act: -0.0001

Data Index: 1193737 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6314. Min Act: -0.0001

Data Index: 879824 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5618. Min Act: -0.0001

Data Index: 42271 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5347. Min Act: -0.0001

Data Index: 1105925 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5499. Min Act: -0.0001

Data Index: 755209 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5697. Min Act: -0.0001

Data Index: 581802 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5339. Min Act: -0.0001

Data Index: 325080 (C4 (Web Text))

Max Activating Token Index: 985

Text #9

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.4959. Min Act: -0.0001

Data Index: 1111173 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.4782. Min Act: -0.0001

Data Index: 241167 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.5068. Min Act: -0.0001

Data Index: 327226 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.4849. Min Act: -0.0001

Data Index: 1254604 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.4570. Min Act: -0.0001

Data Index: 238705 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.4558. Min Act: -0.0001

Data Index: 465409 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.4648. Min Act: -0.0001

Data Index: 562218 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.4524. Min Act: -0.0001

Data Index: 384957 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.4563. Min Act: -0.0001

Data Index: 476964 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.4565. Min Act: -0.0001

Data Index: 114616 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.4369. Min Act: -0.0001

Data Index: 508931 (C4 (Web Text))

Max Activating Token Index: 95