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

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

Neuron 821 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: 1.1493. Min Range: -1.1493

Max Act: 1.1493. Min Act: -0.0001

Data Index: 1638024 (Python Code)

Max Activating Token Index: 360

Text #1

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.1175. Min Act: -0.0001

Data Index: 1592775 (Python Code)

Max Activating Token Index: 49

Text #2

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.0632. Min Act: -0.0001

Data Index: 1605764 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.0221. Min Act: -0.0000

Data Index: 1390520 (Python Code)

Max Activating Token Index: 391

Text #4

Max Range: 1.1493. Min Range: -1.1493

Max Act: 1.0432. Min Act: -0.0001

Data Index: 1393147 (Python Code)

Max Activating Token Index: 744

Text #5

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.9748. Min Act: -0.0001

Data Index: 1372997 (Python Code)

Max Activating Token Index: 668

Text #6

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8657. Min Act: -0.0001

Data Index: 1552096 (Python Code)

Max Activating Token Index: 94

Text #7

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1467283 (Python Code)

Max Activating Token Index: 118

Text #8

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8128. Min Act: -0.0001

Data Index: 1563183 (Python Code)

Max Activating Token Index: 378

Text #9

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1391363 (Python Code)

Max Activating Token Index: 628

Text #10

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8658. Min Act: -0.0000

Data Index: 1616768 (Python Code)

Max Activating Token Index: 106

Text #11

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8671. Min Act: -0.0000

Data Index: 1485876 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8392. Min Act: -0.0001

Data Index: 1455258 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8490. Min Act: -0.0001

Data Index: 1432806 (Python Code)

Max Activating Token Index: 17

Text #14

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8454. Min Act: -0.0000

Data Index: 1511863 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8661. Min Act: -0.0001

Data Index: 1487306 (Python Code)

Max Activating Token Index: 630

Text #16

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8414. Min Act: -0.0001

Data Index: 1495511 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8413. Min Act: -0.0000

Data Index: 1391498 (Python Code)

Max Activating Token Index: 43

Text #18

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8434. Min Act: -0.0001

Data Index: 1410352 (Python Code)

Max Activating Token Index: 959

Text #19

Max Range: 1.1493. Min Range: -1.1493

Max Act: 0.8397. Min Act: -0.0001

Data Index: 1511007 (Python Code)

Max Activating Token Index: 1017