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

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

Neuron 5884 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: 1.6672. Min Range: -1.6672

Max Act: 1.6672. Min Act: -0.0000

Data Index: 1040573 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.6562. Min Act: -0.0000

Data Index: 470902 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.6528. Min Act: -0.0000

Data Index: 960436 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.4147. Min Act: -0.0000

Data Index: 595813 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.1319. Min Act: -0.0000

Data Index: 545625 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.1930. Min Act: -0.0000

Data Index: 1342940 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.1141. Min Act: -0.0000

Data Index: 520234 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.0747. Min Act: -0.0000

Data Index: 820049 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.0517. Min Act: -0.0000

Data Index: 13675 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 1.6672. Min Range: -1.6672

Max Act: 0.9861. Min Act: -0.0000

Data Index: 840354 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.0334. Min Act: -0.0000

Data Index: 262264 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.0099. Min Act: -0.0000

Data Index: 27631 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.0676. Min Act: -0.0000

Data Index: 385158 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.0504. Min Act: -0.0000

Data Index: 1241781 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 1.6672. Min Range: -1.6672

Max Act: 0.9849. Min Act: -0.0000

Data Index: 25230 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.0280. Min Act: -0.0000

Data Index: 902575 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 1.6672. Min Range: -1.6672

Max Act: 0.9633. Min Act: -0.0000

Data Index: 106304 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 1.6672. Min Range: -1.6672

Max Act: 0.9592. Min Act: -0.0000

Data Index: 274989 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 1.6672. Min Range: -1.6672

Max Act: 0.9452. Min Act: -0.0000

Data Index: 740204 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 1.6672. Min Range: -1.6672

Max Act: 1.0138. Min Act: -0.0000

Data Index: 1275184 (C4 (Web Text))

Max Activating Token Index: 349