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

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

Neuron 1371 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2259. Min Range: -2.2259

Max Act: 2.2259. Min Act: -0.0000

Data Index: 1096669 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.9286. Min Act: -0.0000

Data Index: 694806 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.8870. Min Act: -0.0000

Data Index: 1162358 (C4 (Web Text))

Max Activating Token Index: 332

Text #3

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.8570. Min Act: -0.0000

Data Index: 947784 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.8255. Min Act: -0.0000

Data Index: 186080 (C4 (Web Text))

Max Activating Token Index: 601

Text #5

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.8156. Min Act: -0.0000

Data Index: 1284043 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.7335. Min Act: -0.0000

Data Index: 276824 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.6695. Min Act: -0.0000

Data Index: 136985 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.6563. Min Act: -0.0000

Data Index: 604039 (C4 (Web Text))

Max Activating Token Index: 368

Text #9

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.6103. Min Act: -0.0000

Data Index: 774608 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.6902. Min Act: -0.0000

Data Index: 1272225 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.5852. Min Act: -0.0000

Data Index: 1138676 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.5792. Min Act: -0.0000

Data Index: 31549 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.4823. Min Act: -0.0000

Data Index: 1277275 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.5709. Min Act: -0.0000

Data Index: 1119994 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.4690. Min Act: -0.0000

Data Index: 894014 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.5480. Min Act: -0.0000

Data Index: 198048 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.6385. Min Act: -0.0000

Data Index: 1165590 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.6287. Min Act: -0.0000

Data Index: 750130 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 2.2259. Min Range: -2.2259

Max Act: 1.3787. Min Act: -0.0000

Data Index: 114190 (C4 (Web Text))

Max Activating Token Index: 896