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

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

Neuron 1952 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.3423. Min Act: -0.0001

Data Index: 1480366 (Python Code)

Max Activating Token Index: 892

Text #1

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.2495. Min Act: -0.0001

Data Index: 1514848 (Python Code)

Max Activating Token Index: 286

Text #2

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.3201. Min Act: -0.0001

Data Index: 1446602 (Python Code)

Max Activating Token Index: 55

Text #3

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.3945. Min Act: -0.0001

Data Index: 1597017 (Python Code)

Max Activating Token Index: 295

Text #4

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.3140. Min Act: -0.0001

Data Index: 1652650 (Python Code)

Max Activating Token Index: 70

Text #5

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.2485. Min Act: -0.0001

Data Index: 1479481 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.2781. Min Act: -0.0001

Data Index: 1436497 (Python Code)

Max Activating Token Index: 962

Text #7

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1514. Min Act: -0.0001

Data Index: 1581891 (Python Code)

Max Activating Token Index: 590

Text #8

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.2412. Min Act: -0.0001

Data Index: 1532736 (Python Code)

Max Activating Token Index: 476

Text #9

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1939. Min Act: -0.0001

Data Index: 1493877 (Python Code)

Max Activating Token Index: 416

Text #10

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.0996. Min Act: -0.0001

Data Index: 1501903 (Python Code)

Max Activating Token Index: 241

Text #11

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.2330. Min Act: -0.0001

Data Index: 1416291 (Python Code)

Max Activating Token Index: 983

Text #12

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1854. Min Act: -0.0001

Data Index: 1430825 (Python Code)

Max Activating Token Index: 506

Text #13

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.2485. Min Act: -0.0001

Data Index: 1574131 (Python Code)

Max Activating Token Index: 20

Text #14

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.2446. Min Act: -0.0001

Data Index: 1467503 (Python Code)

Max Activating Token Index: 450

Text #15

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1356. Min Act: -0.0001

Data Index: 1622377 (Python Code)

Max Activating Token Index: 906

Text #16

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1620. Min Act: -0.0001

Data Index: 1592617 (Python Code)

Max Activating Token Index: 291

Text #17

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1199. Min Act: -0.0001

Data Index: 1527081 (Python Code)

Max Activating Token Index: 660

Text #18

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.1238. Min Act: -0.0001

Data Index: 1641529 (Python Code)

Max Activating Token Index: 660

Text #19

Max Range: 1.3945. Min Range: -1.3945

Max Act: 1.2209. Min Act: -0.0001

Data Index: 1540911 (Python Code)

Max Activating Token Index: 985