Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1059 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2767. Min Act: -0.0001

Data Index: 1392397 (Python Code)

Max Activating Token Index: 385

Text #1

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2534. Min Act: -0.0001

Data Index: 1468278 (Python Code)

Max Activating Token Index: 133

Text #2

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2352. Min Act: -0.0001

Data Index: 1468440 (Python Code)

Max Activating Token Index: 304

Text #3

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2267. Min Act: -0.0001

Data Index: 1581459 (Python Code)

Max Activating Token Index: 685

Text #4

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1981. Min Act: -0.0001

Data Index: 1520828 (Python Code)

Max Activating Token Index: 254

Text #5

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2065. Min Act: -0.0001

Data Index: 1516024 (Python Code)

Max Activating Token Index: 634

Text #6

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2122. Min Act: -0.0001

Data Index: 1459965 (Python Code)

Max Activating Token Index: 948

Text #7

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2242. Min Act: -0.0001

Data Index: 1398638 (Python Code)

Max Activating Token Index: 244

Text #8

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1926. Min Act: -0.0001

Data Index: 1614056 (Python Code)

Max Activating Token Index: 386

Text #9

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2041. Min Act: -0.0001

Data Index: 1544458 (Python Code)

Max Activating Token Index: 752

Text #10

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1578. Min Act: -0.0001

Data Index: 1557492 (Python Code)

Max Activating Token Index: 614

Text #11

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1909. Min Act: -0.0001

Data Index: 1622437 (Python Code)

Max Activating Token Index: 352

Text #12

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1988. Min Act: -0.0001

Data Index: 1427028 (Python Code)

Max Activating Token Index: 220

Text #13

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.2005. Min Act: -0.0001

Data Index: 1611653 (Python Code)

Max Activating Token Index: 832

Text #14

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1871. Min Act: -0.0001

Data Index: 1390409 (Python Code)

Max Activating Token Index: 199

Text #15

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1934. Min Act: -0.0001

Data Index: 1375366 (Python Code)

Max Activating Token Index: 281

Text #16

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1803. Min Act: -0.0001

Data Index: 1367951 (Python Code)

Max Activating Token Index: 724

Text #17

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1999. Min Act: -0.0001

Data Index: 1426223 (Python Code)

Max Activating Token Index: 444

Text #18

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1918. Min Act: -0.0001

Data Index: 1594633 (Python Code)

Max Activating Token Index: 526

Text #19

Max Range: 0.2767. Min Range: -0.2767

Max Act: 0.1917. Min Act: -0.0001

Data Index: 1594025 (Python Code)

Max Activating Token Index: 418