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

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

Neuron 4670 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.8179. Min Act: -0.0000

Data Index: 270654 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.7187. Min Act: -0.0000

Data Index: 885873 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.5512. Min Act: -0.0000

Data Index: 594434 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.5182. Min Act: -0.0000

Data Index: 1070327 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.4229. Min Act: -0.0000

Data Index: 1233593 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.4549. Min Act: -0.0000

Data Index: 423479 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.4280. Min Act: -0.0000

Data Index: 958556 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.4013. Min Act: -0.0000

Data Index: 1347801 (C4 (Web Text))

Max Activating Token Index: 589

Text #8

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.3517. Min Act: -0.0000

Data Index: 1069654 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.3356. Min Act: -0.0000

Data Index: 494800 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.3108. Min Act: -0.0000

Data Index: 207353 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.2701. Min Act: -0.0000

Data Index: 587712 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.1942. Min Act: -0.0000

Data Index: 824091 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.2857. Min Act: -0.0000

Data Index: 229989 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.1690. Min Act: -0.0000

Data Index: 1312786 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.2270. Min Act: -0.0000

Data Index: 254617 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.1468. Min Act: -0.0000

Data Index: 877010 (C4 (Web Text))

Max Activating Token Index: 713

Text #17

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.1459. Min Act: -0.0000

Data Index: 967121 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.1733. Min Act: -0.0000

Data Index: 846269 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 1.8179. Min Range: -1.8179

Max Act: 1.1396. Min Act: -0.0000

Data Index: 1176932 (C4 (Web Text))

Max Activating Token Index: 213