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

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

Neuron 2033 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.2263. Min Act: -0.0000

Data Index: 1631431 (Python Code)

Max Activating Token Index: 234

Text #1

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.1254. Min Act: -0.0000

Data Index: 1470159 (Python Code)

Max Activating Token Index: 956

Text #2

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.1763. Min Act: -0.0000

Data Index: 1402392 (Python Code)

Max Activating Token Index: 835

Text #3

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.1061. Min Act: -0.0000

Data Index: 1383124 (Python Code)

Max Activating Token Index: 251

Text #4

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.0427. Min Act: -0.0000

Data Index: 1369663 (Python Code)

Max Activating Token Index: 355

Text #5

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.0502. Min Act: -0.0000

Data Index: 1633471 (Python Code)

Max Activating Token Index: 709

Text #6

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1412499 (Python Code)

Max Activating Token Index: 149

Text #7

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9591. Min Act: -0.0000

Data Index: 1381097 (Python Code)

Max Activating Token Index: 923

Text #8

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9203. Min Act: -0.0000

Data Index: 1474747 (Python Code)

Max Activating Token Index: 739

Text #9

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9861. Min Act: -0.0000

Data Index: 1402570 (Python Code)

Max Activating Token Index: 236

Text #10

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9391. Min Act: -0.0000

Data Index: 1629070 (Python Code)

Max Activating Token Index: 695

Text #11

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9278. Min Act: -0.0000

Data Index: 1554947 (Python Code)

Max Activating Token Index: 103

Text #12

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9107. Min Act: -0.0000

Data Index: 1367570 (Python Code)

Max Activating Token Index: 195

Text #13

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1536030 (Python Code)

Max Activating Token Index: 8

Text #14

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1536822 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1546568 (Python Code)

Max Activating Token Index: 285

Text #16

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8587. Min Act: -0.0000

Data Index: 1450029 (Python Code)

Max Activating Token Index: 498

Text #17

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1371187 (Python Code)

Max Activating Token Index: 603

Text #18

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1372726 (Python Code)

Max Activating Token Index: 1013

Text #19

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1411551 (Python Code)

Max Activating Token Index: 47