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

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

Neuron 5366 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.3773. Min Act: -0.0000

Data Index: 1576553 (Python Code)

Max Activating Token Index: 986

Text #1

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.2683. Min Act: -0.0000

Data Index: 1586068 (Python Code)

Max Activating Token Index: 326

Text #2

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.1951. Min Act: -0.0000

Data Index: 1530125 (Python Code)

Max Activating Token Index: 265

Text #3

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.2905. Min Act: -0.0000

Data Index: 1449529 (Python Code)

Max Activating Token Index: 162

Text #4

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.2441. Min Act: -0.0000

Data Index: 1413383 (Python Code)

Max Activating Token Index: 155

Text #5

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.2536. Min Act: -0.0000

Data Index: 1489737 (Python Code)

Max Activating Token Index: 601

Text #6

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.2255. Min Act: -0.0000

Data Index: 1463164 (Python Code)

Max Activating Token Index: 1017

Text #7

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.1937. Min Act: -0.0000

Data Index: 1421800 (Python Code)

Max Activating Token Index: 706

Text #8

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.1647. Min Act: -0.0000

Data Index: 1394391 (Python Code)

Max Activating Token Index: 483

Text #9

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.1212. Min Act: -0.0000

Data Index: 1581585 (Python Code)

Max Activating Token Index: 121

Text #10

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.1292. Min Act: -0.0000

Data Index: 1432097 (Python Code)

Max Activating Token Index: 758

Text #11

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1379945 (Python Code)

Max Activating Token Index: 823

Text #12

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1515662 (Python Code)

Max Activating Token Index: 845

Text #13

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1412212 (Python Code)

Max Activating Token Index: 961

Text #14

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1429269 (Python Code)

Max Activating Token Index: 342

Text #15

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.0246. Min Act: -0.0000

Data Index: 1609343 (Python Code)

Max Activating Token Index: 539

Text #16

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.0201. Min Act: -0.0000

Data Index: 1484206 (Python Code)

Max Activating Token Index: 968

Text #17

Max Range: 1.3773. Min Range: -1.3773

Max Act: 1.0225. Min Act: -0.0000

Data Index: 1587153 (Python Code)

Max Activating Token Index: 1005

Text #18

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.9933. Min Act: -0.0000

Data Index: 1633771 (Python Code)

Max Activating Token Index: 175

Text #19

Max Range: 1.3773. Min Range: -1.3773

Max Act: 0.9638. Min Act: -0.0000

Data Index: 1593512 (Python Code)

Max Activating Token Index: 800