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

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

Neuron 554 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.3358. Min Act: -0.0001

Data Index: 414668 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2947. Min Act: -0.0001

Data Index: 223480 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2770. Min Act: -0.0001

Data Index: 775960 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2562. Min Act: -0.0001

Data Index: 984997 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2789. Min Act: -0.0001

Data Index: 1349615 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2849. Min Act: -0.0001

Data Index: 689479 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2805. Min Act: -0.0001

Data Index: 1320884 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2834. Min Act: -0.0001

Data Index: 60884 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2650. Min Act: -0.0001

Data Index: 1013762 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2575. Min Act: -0.0001

Data Index: 58621 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2916. Min Act: -0.0001

Data Index: 989784 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2439. Min Act: -0.0001

Data Index: 1042536 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2886. Min Act: -0.0001

Data Index: 959884 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2559. Min Act: -0.0001

Data Index: 526203 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2700. Min Act: -0.0001

Data Index: 399125 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2655. Min Act: -0.0001

Data Index: 855365 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2659. Min Act: -0.0001

Data Index: 1329884 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2676. Min Act: -0.0001

Data Index: 640172 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2459. Min Act: -0.0001

Data Index: 333902 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2658. Min Act: -0.0001

Data Index: 1183315 (C4 (Web Text))

Max Activating Token Index: 886