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

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

Neuron 5004 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.7988. Min Act: -0.0000

Data Index: 573342 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6472. Min Act: -0.0000

Data Index: 344410 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.6053. Min Act: -0.0000

Data Index: 554332 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5346. Min Act: -0.0000

Data Index: 290151 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5324. Min Act: -0.0000

Data Index: 255045 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5398. Min Act: -0.0000

Data Index: 467627 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5266. Min Act: -0.0000

Data Index: 151999 (C4 (Web Text))

Max Activating Token Index: 487

Text #7

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1277688 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1344002 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1355267 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5154. Min Act: -0.0000

Data Index: 252665 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5207. Min Act: -0.0000

Data Index: 501701 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1204896 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.5182. Min Act: -0.0000

Data Index: 614532 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.4700. Min Act: -0.0000

Data Index: 835985 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.4945. Min Act: -0.0000

Data Index: 233963 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.4697. Min Act: -0.0000

Data Index: 972909 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.4669. Min Act: -0.0000

Data Index: 189217 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.4410. Min Act: -0.0000

Data Index: 72178 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 0.7988. Min Range: -0.7988

Max Act: 0.4352. Min Act: -0.0000

Data Index: 542295 (C4 (Web Text))

Max Activating Token Index: 118