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

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

Neuron 5638 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: 0.9680. Min Range: -0.9680

Max Act: 0.9680. Min Act: -0.0000

Data Index: 333586 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8737. Min Act: -0.0000

Data Index: 1036410 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8282. Min Act: -0.0000

Data Index: 167701 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.8173. Min Act: -0.0000

Data Index: 188637 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.9020. Min Act: -0.0000

Data Index: 601512 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1339249 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7212. Min Act: -0.0000

Data Index: 64789 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7638. Min Act: -0.0000

Data Index: 82911 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7122. Min Act: -0.0000

Data Index: 1144644 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7554. Min Act: -0.0000

Data Index: 1323977 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1107805 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7221. Min Act: -0.0000

Data Index: 448491 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7253. Min Act: -0.0000

Data Index: 632672 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.6780. Min Act: -0.0000

Data Index: 192634 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7299. Min Act: -0.0000

Data Index: 269760 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.7446. Min Act: -0.0000

Data Index: 446358 (C4 (Web Text))

Max Activating Token Index: 693

Text #16

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.6290. Min Act: -0.0000

Data Index: 446698 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.6766. Min Act: -0.0000

Data Index: 707755 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1033916 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.9680. Min Range: -0.9680

Max Act: 0.6268. Min Act: -0.0000

Data Index: 898970 (C4 (Web Text))

Max Activating Token Index: 430