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

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

Neuron 2251 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: 3.1242. Min Range: -3.1242

Max Act: 3.1242. Min Act: -0.0000

Data Index: 1431252 (Python Code)

Max Activating Token Index: 166

Text #1

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.9717. Min Act: -0.0000

Data Index: 1595565 (Python Code)

Max Activating Token Index: 80

Text #2

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.8179. Min Act: -0.0000

Data Index: 1461620 (Python Code)

Max Activating Token Index: 362

Text #3

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.6418. Min Act: -0.0000

Data Index: 1597598 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.5687. Min Act: -0.0000

Data Index: 1648612 (Python Code)

Max Activating Token Index: 115

Text #5

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.2918. Min Act: -0.0000

Data Index: 1549892 (Python Code)

Max Activating Token Index: 317

Text #6

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.3520. Min Act: -0.0000

Data Index: 1408533 (Python Code)

Max Activating Token Index: 672

Text #7

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.3475. Min Act: -0.0000

Data Index: 1594140 (Python Code)

Max Activating Token Index: 222

Text #8

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.2975. Min Act: -0.0000

Data Index: 1571269 (Python Code)

Max Activating Token Index: 506

Text #9

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.1947. Min Act: -0.0000

Data Index: 1655001 (Python Code)

Max Activating Token Index: 319

Text #10

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.2534. Min Act: -0.0000

Data Index: 1549193 (Python Code)

Max Activating Token Index: 88

Text #11

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.2317. Min Act: -0.0000

Data Index: 1478374 (Python Code)

Max Activating Token Index: 637

Text #12

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.0100. Min Act: -0.0000

Data Index: 1457510 (Python Code)

Max Activating Token Index: 857

Text #13

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.3434. Min Act: -0.0000

Data Index: 1437498 (Python Code)

Max Activating Token Index: 849

Text #14

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.1970. Min Act: -0.0000

Data Index: 1496434 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.1692. Min Act: -0.0000

Data Index: 1381102 (Python Code)

Max Activating Token Index: 18

Text #16

Max Range: 3.1242. Min Range: -3.1242

Max Act: 1.7162. Min Act: -0.0000

Data Index: 1629949 (Python Code)

Max Activating Token Index: 788

Text #17

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.2451. Min Act: -0.0000

Data Index: 1631316 (Python Code)

Max Activating Token Index: 185

Text #18

Max Range: 3.1242. Min Range: -3.1242

Max Act: 1.9993. Min Act: -0.0000

Data Index: 1438270 (Python Code)

Max Activating Token Index: 740

Text #19

Max Range: 3.1242. Min Range: -3.1242

Max Act: 2.0960. Min Act: -0.0000

Data Index: 1394511 (Python Code)

Max Activating Token Index: 177