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

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

Neuron 1497 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2638. Min Act: -0.0001

Data Index: 1558259 (Python Code)

Max Activating Token Index: 359

Text #1

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2592. Min Act: -0.0001

Data Index: 1581267 (Python Code)

Max Activating Token Index: 502

Text #2

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2721. Min Act: -0.0001

Data Index: 1656412 (Python Code)

Max Activating Token Index: 44

Text #3

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2229. Min Act: -0.0001

Data Index: 1539743 (Python Code)

Max Activating Token Index: 894

Text #4

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2367. Min Act: -0.0001

Data Index: 1487905 (Python Code)

Max Activating Token Index: 647

Text #5

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2211. Min Act: -0.0001

Data Index: 1429629 (Python Code)

Max Activating Token Index: 1018

Text #6

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2191. Min Act: -0.0001

Data Index: 1451891 (Python Code)

Max Activating Token Index: 353

Text #7

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2163. Min Act: -0.0001

Data Index: 1418935 (Python Code)

Max Activating Token Index: 915

Text #8

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2242. Min Act: -0.0001

Data Index: 1529530 (Python Code)

Max Activating Token Index: 465

Text #9

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2120. Min Act: -0.0001

Data Index: 1470561 (Python Code)

Max Activating Token Index: 199

Text #10

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2111. Min Act: -0.0001

Data Index: 1392544 (Python Code)

Max Activating Token Index: 456

Text #11

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2084. Min Act: -0.0001

Data Index: 1401796 (Python Code)

Max Activating Token Index: 73

Text #12

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.2023. Min Act: -0.0001

Data Index: 1379813 (Python Code)

Max Activating Token Index: 499

Text #13

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1951. Min Act: -0.0001

Data Index: 1466283 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1257. Min Act: -0.0001

Data Index: 1461208 (Python Code)

Max Activating Token Index: 829

Text #15

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1937. Min Act: -0.0001

Data Index: 1443298 (Python Code)

Max Activating Token Index: 194

Text #16

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1865. Min Act: -0.0001

Data Index: 1555659 (Python Code)

Max Activating Token Index: 208

Text #17

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1902. Min Act: -0.0001

Data Index: 1555496 (Python Code)

Max Activating Token Index: 22

Text #18

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1808. Min Act: -0.0001

Data Index: 1650151 (Python Code)

Max Activating Token Index: 162

Text #19

Max Range: 0.2721. Min Range: -0.2721

Max Act: 0.1673. Min Act: -0.0001

Data Index: 1548176 (Python Code)

Max Activating Token Index: 861