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

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

Neuron 3141 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: 0.6977. Min Range: -0.6977

Max Act: 0.6977. Min Act: -0.0001

Data Index: 1139316 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5886. Min Act: -0.0001

Data Index: 408074 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5660. Min Act: -0.0001

Data Index: 517767 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5688. Min Act: -0.0001

Data Index: 541145 (C4 (Web Text))

Max Activating Token Index: 632

Text #4

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5466. Min Act: -0.0001

Data Index: 1024326 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5601. Min Act: -0.0001

Data Index: 26288 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5461. Min Act: -0.0001

Data Index: 171687 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5258. Min Act: -0.0001

Data Index: 896342 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5242. Min Act: -0.0001

Data Index: 115429 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5137. Min Act: -0.0001

Data Index: 972021 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5159. Min Act: -0.0001

Data Index: 1136453 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5503. Min Act: -0.0001

Data Index: 706520 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5371. Min Act: -0.0001

Data Index: 276380 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5346. Min Act: -0.0001

Data Index: 1028227 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5080. Min Act: -0.0001

Data Index: 755163 (C4 (Web Text))

Max Activating Token Index: 261

Text #15

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5273. Min Act: -0.0001

Data Index: 659453 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5195. Min Act: -0.0001

Data Index: 1419488 (Python Code)

Max Activating Token Index: 534

Text #17

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5219. Min Act: -0.0001

Data Index: 458960 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5178. Min Act: -0.0001

Data Index: 386006 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.6977. Min Range: -0.6977

Max Act: 0.5203. Min Act: -0.0001

Data Index: 272625 (C4 (Web Text))

Max Activating Token Index: 84