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

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

Neuron 5112 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: 2.4600. Min Range: -2.4600

Max Act: 2.4600. Min Act: -0.0000

Data Index: 1565492 (Python Code)

Max Activating Token Index: 15

Text #1

Max Range: 2.4600. Min Range: -2.4600

Max Act: 2.3427. Min Act: -0.0000

Data Index: 1621147 (Python Code)

Max Activating Token Index: 267

Text #2

Max Range: 2.4600. Min Range: -2.4600

Max Act: 2.0297. Min Act: -0.0000

Data Index: 1425572 (Python Code)

Max Activating Token Index: 739

Text #3

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.9549. Min Act: -0.0001

Data Index: 1441665 (Python Code)

Max Activating Token Index: 282

Text #4

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.9315. Min Act: -0.0001

Data Index: 1566018 (Python Code)

Max Activating Token Index: 9

Text #5

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.8101. Min Act: -0.0000

Data Index: 1629880 (Python Code)

Max Activating Token Index: 52

Text #6

Max Range: 2.4600. Min Range: -2.4600

Max Act: 2.0119. Min Act: -0.0001

Data Index: 1489877 (Python Code)

Max Activating Token Index: 124

Text #7

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.8808. Min Act: -0.0001

Data Index: 1407606 (Python Code)

Max Activating Token Index: 153

Text #8

Max Range: 2.4600. Min Range: -2.4600

Max Act: 2.0316. Min Act: -0.0000

Data Index: 1507143 (Python Code)

Max Activating Token Index: 1021

Text #9

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.6674. Min Act: -0.0000

Data Index: 1586705 (Python Code)

Max Activating Token Index: 125

Text #10

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.7518. Min Act: -0.0001

Data Index: 1603963 (Python Code)

Max Activating Token Index: 836

Text #11

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.6342. Min Act: -0.0001

Data Index: 1450691 (Python Code)

Max Activating Token Index: 881

Text #12

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.7295. Min Act: -0.0000

Data Index: 521654 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.6682. Min Act: -0.0001

Data Index: 692667 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.7389. Min Act: -0.0000

Data Index: 1416668 (Python Code)

Max Activating Token Index: 153

Text #15

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.6177. Min Act: -0.0001

Data Index: 1612185 (Python Code)

Max Activating Token Index: 131

Text #16

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.8049. Min Act: -0.0000

Data Index: 1639100 (Python Code)

Max Activating Token Index: 911

Text #17

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.5170. Min Act: -0.0000

Data Index: 1557355 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.4913. Min Act: -0.0000

Data Index: 1547976 (Python Code)

Max Activating Token Index: 131

Text #19

Max Range: 2.4600. Min Range: -2.4600

Max Act: 1.4944. Min Act: -0.0001

Data Index: 1526946 (Python Code)

Max Activating Token Index: 115