Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4416 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.6780. Min Act: -0.0000

Data Index: 632781 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.6634. Min Act: -0.0000

Data Index: 601272 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.6803. Min Act: -0.0000

Data Index: 308146 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.5178. Min Act: -0.0000

Data Index: 472463 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.3985. Min Act: -0.0000

Data Index: 891627 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.4603. Min Act: -0.0000

Data Index: 923436 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.3688. Min Act: -0.0000

Data Index: 72564 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.4401. Min Act: -0.0000

Data Index: 580302 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.4034. Min Act: -0.0000

Data Index: 781735 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.4346. Min Act: -0.0000

Data Index: 297984 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.3434. Min Act: -0.0000

Data Index: 972877 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.4831. Min Act: -0.0000

Data Index: 1014232 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.3985. Min Act: -0.0000

Data Index: 70602 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.5259. Min Act: -0.0001

Data Index: 219198 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.4376. Min Act: -0.0000

Data Index: 553692 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.5336. Min Act: -0.0000

Data Index: 667728 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.3474. Min Act: -0.0000

Data Index: 1217377 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.3701. Min Act: -0.0000

Data Index: 1120928 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.1612. Min Act: -0.0000

Data Index: 109175 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 1.6803. Min Range: -1.6803

Max Act: 1.4687. Min Act: -0.0000

Data Index: 1292843 (C4 (Web Text))

Max Activating Token Index: 665