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

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

Neuron 965 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.4399. Min Act: -0.0000

Data Index: 1603950 (Python Code)

Max Activating Token Index: 237

Text #1

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.8099. Min Act: -0.0000

Data Index: 1508398 (Python Code)

Max Activating Token Index: 898

Text #2

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.8685. Min Act: -0.0000

Data Index: 1456169 (Python Code)

Max Activating Token Index: 97

Text #3

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.7425. Min Act: -0.0000

Data Index: 1367918 (Python Code)

Max Activating Token Index: 351

Text #4

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.8561. Min Act: -0.0000

Data Index: 1641509 (Python Code)

Max Activating Token Index: 389

Text #5

Max Range: 3.4399. Min Range: -3.4399

Max Act: 3.0942. Min Act: -0.0000

Data Index: 1467587 (Python Code)

Max Activating Token Index: 849

Text #6

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.5311. Min Act: -0.0000

Data Index: 1525281 (Python Code)

Max Activating Token Index: 933

Text #7

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.5884. Min Act: -0.0000

Data Index: 1430243 (Python Code)

Max Activating Token Index: 793

Text #8

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.5508. Min Act: -0.0000

Data Index: 1488533 (Python Code)

Max Activating Token Index: 563

Text #9

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.6587. Min Act: -0.0000

Data Index: 1503208 (Python Code)

Max Activating Token Index: 973

Text #10

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.0212. Min Act: -0.0000

Data Index: 1360471 (Python Code)

Max Activating Token Index: 707

Text #11

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.5639. Min Act: -0.0000

Data Index: 1614233 (Python Code)

Max Activating Token Index: 185

Text #12

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.5764. Min Act: -0.0000

Data Index: 1597655 (Python Code)

Max Activating Token Index: 808

Text #13

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.6534. Min Act: -0.0000

Data Index: 1604993 (Python Code)

Max Activating Token Index: 890

Text #14

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.4977. Min Act: -0.0000

Data Index: 1596056 (Python Code)

Max Activating Token Index: 487

Text #15

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.3192. Min Act: -0.0000

Data Index: 1458427 (Python Code)

Max Activating Token Index: 228

Text #16

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.4642. Min Act: -0.0000

Data Index: 1574990 (Python Code)

Max Activating Token Index: 29

Text #17

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.4180. Min Act: -0.0000

Data Index: 1365280 (Python Code)

Max Activating Token Index: 143

Text #18

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.3131. Min Act: -0.0000

Data Index: 1464134 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 3.4399. Min Range: -3.4399

Max Act: 2.4243. Min Act: -0.0000

Data Index: 1481101 (Python Code)

Max Activating Token Index: 270