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

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

Neuron 645 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: 1.4502. Min Range: -1.4502

Max Act: 1.2736. Min Act: -0.0001

Data Index: 948726 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.3207. Min Act: -0.0001

Data Index: 1134334 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.2024. Min Act: -0.0001

Data Index: 1279397 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.2584. Min Act: -0.0001

Data Index: 842577 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.4502. Min Act: -0.0001

Data Index: 1024390 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.1237. Min Act: -0.0001

Data Index: 550648 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.3136. Min Act: -0.0001

Data Index: 1247522 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.2291. Min Act: -0.0001

Data Index: 679859 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.2208. Min Act: -0.0000

Data Index: 155593 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.2537. Min Act: -0.0001

Data Index: 162561 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.1686. Min Act: -0.0001

Data Index: 1190462 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.3148. Min Act: -0.0001

Data Index: 253264 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.1235. Min Act: -0.0001

Data Index: 786782 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.1276. Min Act: -0.0001

Data Index: 937249 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.0800. Min Act: -0.0001

Data Index: 286955 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.1491. Min Act: -0.0001

Data Index: 408673 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.1783. Min Act: -0.0001

Data Index: 727507 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.1555. Min Act: -0.0001

Data Index: 201617 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.1224. Min Act: -0.0001

Data Index: 973646 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 1.4502. Min Range: -1.4502

Max Act: 1.0431. Min Act: -0.0001

Data Index: 485509 (C4 (Web Text))

Max Activating Token Index: 934