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

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

Neuron 4458 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1214962 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1956. Min Act: -0.0000

Data Index: 296911 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1005184 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1779. Min Act: -0.0000

Data Index: 738828 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1693. Min Act: -0.0000

Data Index: 554708 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1728. Min Act: -0.0000

Data Index: 236559 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1549. Min Act: -0.0000

Data Index: 634403 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1528. Min Act: -0.0000

Data Index: 268032 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1461. Min Act: -0.0000

Data Index: 397803 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1519. Min Act: -0.0000

Data Index: 579854 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1419. Min Act: -0.0000

Data Index: 330797 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1523. Min Act: -0.0000

Data Index: 1230436 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1329765 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1459. Min Act: -0.0000

Data Index: 848900 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1414. Min Act: -0.0000

Data Index: 912842 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1361. Min Act: -0.0000

Data Index: 834881 (C4 (Web Text))

Max Activating Token Index: 632

Text #16

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1344. Min Act: -0.0000

Data Index: 772099 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1293. Min Act: -0.0000

Data Index: 149216 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1257. Min Act: -0.0000

Data Index: 165264 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.2902. Min Range: -0.2902

Max Act: 0.1347. Min Act: -0.0000

Data Index: 529780 (C4 (Web Text))

Max Activating Token Index: 500