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

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

Neuron 971 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.2298. Min Act: -0.0001

Data Index: 787088 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1914. Min Act: -0.0000

Data Index: 201367 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1245332 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1810. Min Act: -0.0001

Data Index: 286736 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1800. Min Act: -0.0000

Data Index: 676732 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1793. Min Act: -0.0000

Data Index: 937110 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1737. Min Act: -0.0000

Data Index: 938473 (C4 (Web Text))

Max Activating Token Index: 178

Text #7

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1635. Min Act: -0.0000

Data Index: 151863 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1715. Min Act: -0.0000

Data Index: 645404 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1608. Min Act: -0.0001

Data Index: 621429 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1522. Min Act: -0.0001

Data Index: 227597 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1601. Min Act: -0.0000

Data Index: 67145 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1573. Min Act: -0.0001

Data Index: 664717 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1468. Min Act: -0.0001

Data Index: 260562 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1478. Min Act: -0.0001

Data Index: 172483 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1265324 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1465. Min Act: -0.0001

Data Index: 998076 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1454. Min Act: -0.0001

Data Index: 691277 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1383. Min Act: -0.0001

Data Index: 786323 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.2298. Min Range: -0.2298

Max Act: 0.1477. Min Act: -0.0001

Data Index: 369480 (C4 (Web Text))

Max Activating Token Index: 912