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

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

Neuron 3938 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: 2.3312. Min Range: -2.3312

Max Act: 2.3312. Min Act: -0.0001

Data Index: 1364038 (Python Code)

Max Activating Token Index: 676

Text #1

Max Range: 2.3312. Min Range: -2.3312

Max Act: 2.2379. Min Act: -0.0000

Data Index: 1591332 (Python Code)

Max Activating Token Index: 282

Text #2

Max Range: 2.3312. Min Range: -2.3312

Max Act: 2.0903. Min Act: -0.0000

Data Index: 1448386 (Python Code)

Max Activating Token Index: 26

Text #3

Max Range: 2.3312. Min Range: -2.3312

Max Act: 2.3310. Min Act: -0.0001

Data Index: 1569619 (Python Code)

Max Activating Token Index: 121

Text #4

Max Range: 2.3312. Min Range: -2.3312

Max Act: 2.0034. Min Act: -0.0000

Data Index: 1556329 (Python Code)

Max Activating Token Index: 872

Text #5

Max Range: 2.3312. Min Range: -2.3312

Max Act: 2.0867. Min Act: -0.0000

Data Index: 1538282 (Python Code)

Max Activating Token Index: 467

Text #6

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.9419. Min Act: -0.0000

Data Index: 1489048 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.8636. Min Act: -0.0000

Data Index: 1416442 (Python Code)

Max Activating Token Index: 365

Text #8

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.9030. Min Act: -0.0001

Data Index: 1425787 (Python Code)

Max Activating Token Index: 66

Text #9

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.7395. Min Act: -0.0000

Data Index: 1474411 (Python Code)

Max Activating Token Index: 660

Text #10

Max Range: 2.3312. Min Range: -2.3312

Max Act: 2.0104. Min Act: -0.0001

Data Index: 1375951 (Python Code)

Max Activating Token Index: 106

Text #11

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.8281. Min Act: -0.0001

Data Index: 1628391 (Python Code)

Max Activating Token Index: 700

Text #12

Max Range: 2.3312. Min Range: -2.3312

Max Act: 2.0613. Min Act: -0.0000

Data Index: 1589305 (Python Code)

Max Activating Token Index: 145

Text #13

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.7273. Min Act: -0.0000

Data Index: 1478181 (Python Code)

Max Activating Token Index: 547

Text #14

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.7799. Min Act: -0.0001

Data Index: 1466110 (Python Code)

Max Activating Token Index: 195

Text #15

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.5683. Min Act: -0.0000

Data Index: 1474156 (Python Code)

Max Activating Token Index: 355

Text #16

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.8822. Min Act: -0.0001

Data Index: 1449444 (Python Code)

Max Activating Token Index: 769

Text #17

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.6502. Min Act: -0.0000

Data Index: 1637767 (Python Code)

Max Activating Token Index: 865

Text #18

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.8943. Min Act: -0.0000

Data Index: 1509581 (Python Code)

Max Activating Token Index: 205

Text #19

Max Range: 2.3312. Min Range: -2.3312

Max Act: 1.8829. Min Act: -0.0000

Data Index: 1559246 (Python Code)

Max Activating Token Index: 393