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

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

Neuron 5387 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2291. Min Act: -0.0000

Data Index: 505518 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2298. Min Act: -0.0000

Data Index: 367859 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1570147 (Python Code)

Max Activating Token Index: 853

Text #3

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2282. Min Act: -0.0000

Data Index: 1097738 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2175. Min Act: -0.0000

Data Index: 863353 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1933. Min Act: -0.0000

Data Index: 613480 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2097. Min Act: -0.0000

Data Index: 731681 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1361640 (Python Code)

Max Activating Token Index: 944

Text #8

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1077583 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.2015. Min Act: -0.0000

Data Index: 540503 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1366905 (Python Code)

Max Activating Token Index: 554

Text #11

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1378402 (Python Code)

Max Activating Token Index: 830

Text #12

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1431586 (Python Code)

Max Activating Token Index: 554

Text #13

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1652568 (Python Code)

Max Activating Token Index: 608

Text #14

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1879. Min Act: -0.0000

Data Index: 1467386 (Python Code)

Max Activating Token Index: 469

Text #15

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1653. Min Act: -0.0000

Data Index: 457973 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1764. Min Act: -0.0000

Data Index: 871578 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1338366 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1644. Min Act: -0.0000

Data Index: 679847 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.2310. Min Range: -0.2310

Max Act: 0.1788. Min Act: -0.0000

Data Index: 622199 (C4 (Web Text))

Max Activating Token Index: 496