Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3067 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0529. Min Act: -0.0004

Data Index: 183112 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0410. Min Act: -0.0004

Data Index: 1191024 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0354. Min Act: -0.0004

Data Index: 260858 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0360. Min Act: -0.0004

Data Index: 1039863 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0343. Min Act: -0.0004

Data Index: 623903 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0333. Min Act: -0.0004

Data Index: 341183 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0321. Min Act: -0.0004

Data Index: 192864 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0301. Min Act: -0.0004

Data Index: 465263 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0309. Min Act: -0.0004

Data Index: 729409 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0322. Min Act: -0.0004

Data Index: 416775 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0286. Min Act: -0.0004

Data Index: 438191 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0292. Min Act: -0.0004

Data Index: 193396 (C4 (Web Text))

Max Activating Token Index: 497

Text #12

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0291. Min Act: -0.0004

Data Index: 151798 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0296. Min Act: -0.0004

Data Index: 465731 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0279. Min Act: -0.0004

Data Index: 1303959 (C4 (Web Text))

Max Activating Token Index: 437

Text #15

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0275. Min Act: -0.0004

Data Index: 912679 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0283. Min Act: -0.0004

Data Index: 442998 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0265. Min Act: -0.0004

Data Index: 1217986 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0277. Min Act: -0.0004

Data Index: 1242121 (C4 (Web Text))

Max Activating Token Index: 510

Text #19

Max Range: 0.0529. Min Range: -0.0529

Max Act: 0.0274. Min Act: -0.0004

Data Index: 1311216 (C4 (Web Text))

Max Activating Token Index: 410