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

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

Neuron 938 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.9030. Min Act: -0.0001

Data Index: 694866 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.7988. Min Act: -0.0001

Data Index: 300386 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.7108. Min Act: -0.0001

Data Index: 959582 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.4069. Min Act: -0.0001

Data Index: 755185 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.3628. Min Act: -0.0001

Data Index: 742014 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.2180. Min Act: -0.0001

Data Index: 442590 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.2666. Min Act: -0.0001

Data Index: 769615 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.2436. Min Act: -0.0001

Data Index: 1300138 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.2144. Min Act: -0.0001

Data Index: 386400 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.2754. Min Act: -0.0001

Data Index: 907453 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.1265. Min Act: -0.0001

Data Index: 1039216 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.1917. Min Act: -0.0001

Data Index: 133142 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.1686. Min Act: -0.0001

Data Index: 820146 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.2514. Min Act: -0.0001

Data Index: 139528 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.1756. Min Act: -0.0001

Data Index: 683539 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.0997. Min Act: -0.0001

Data Index: 750417 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.1500. Min Act: -0.0001

Data Index: 330061 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.2289. Min Act: -0.0001

Data Index: 1140294 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.0972. Min Act: -0.0001

Data Index: 198751 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 1.9030. Min Range: -1.9030

Max Act: 1.1362. Min Act: -0.0001

Data Index: 589730 (C4 (Web Text))

Max Activating Token Index: 288