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

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

Neuron 4152 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: 0.4202. Min Range: -0.4202

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1038295 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.3001. Min Act: -0.0000

Data Index: 895395 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2909. Min Act: -0.0000

Data Index: 1153426 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2918. Min Act: -0.0000

Data Index: 386323 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2846. Min Act: -0.0000

Data Index: 917829 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1302430 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2708. Min Act: -0.0000

Data Index: 86314 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2952. Min Act: -0.0000

Data Index: 615301 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2465. Min Act: -0.0000

Data Index: 624620 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2521. Min Act: -0.0000

Data Index: 546876 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2506. Min Act: -0.0000

Data Index: 470538 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2777. Min Act: -0.0000

Data Index: 930447 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2595. Min Act: -0.0000

Data Index: 999206 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2640. Min Act: -0.0000

Data Index: 948802 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2635. Min Act: -0.0000

Data Index: 657440 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2703. Min Act: -0.0000

Data Index: 372072 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2536. Min Act: -0.0000

Data Index: 83819 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2625. Min Act: -0.0000

Data Index: 109051 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2540. Min Act: -0.0000

Data Index: 84305 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.4202. Min Range: -0.4202

Max Act: 0.2507. Min Act: -0.0000

Data Index: 522912 (C4 (Web Text))

Max Activating Token Index: 300