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

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

Neuron 3378 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: 2.1883. Min Range: -2.1883

Max Act: 2.1380. Min Act: -0.0000

Data Index: 1368091 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 2.1883. Min Range: -2.1883

Max Act: 2.1341. Min Act: -0.0000

Data Index: 1537830 (Python Code)

Max Activating Token Index: 162

Text #2

Max Range: 2.1883. Min Range: -2.1883

Max Act: 2.1883. Min Act: -0.0000

Data Index: 1601296 (Python Code)

Max Activating Token Index: 57

Text #3

Max Range: 2.1883. Min Range: -2.1883

Max Act: 2.1235. Min Act: -0.0000

Data Index: 1415512 (Python Code)

Max Activating Token Index: 104

Text #4

Max Range: 2.1883. Min Range: -2.1883

Max Act: 1.6989. Min Act: -0.0001

Data Index: 1350580 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 2.1883. Min Range: -2.1883

Max Act: 1.9090. Min Act: -0.0000

Data Index: 1499508 (Python Code)

Max Activating Token Index: 85

Text #6

Max Range: 2.1883. Min Range: -2.1883

Max Act: 1.8832. Min Act: -0.0000

Data Index: 1398424 (Python Code)

Max Activating Token Index: 134

Text #7

Max Range: 2.1883. Min Range: -2.1883

Max Act: 1.7637. Min Act: -0.0000

Data Index: 1647052 (Python Code)

Max Activating Token Index: 440

Text #8

Max Range: 2.1883. Min Range: -2.1883

Max Act: 1.8518. Min Act: -0.0000

Data Index: 1432826 (Python Code)

Max Activating Token Index: 54

Text #9

Max Range: 2.1883. Min Range: -2.1883

Max Act: 1.7662. Min Act: -0.0000

Data Index: 1506617 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 2.1883. Min Range: -2.1883

Max Act: 1.6675. Min Act: -0.0000

Data Index: 1620136 (Python Code)

Max Activating Token Index: 888

Text #11

Max Range: 2.1883. Min Range: -2.1883

Max Act: 1.7755. Min Act: -0.0000

Data Index: 1454324 (Python Code)

Max Activating Token Index: 250

Text #12

Max Range: 2.1883. Min Range: -2.1883

Max Act: 1.6557. Min Act: -0.0000

Data Index: 1461938 (Python Code)

Max Activating Token Index: 117

Text #13

Max Range: 2.1883. Min Range: -2.1883

Max Act: 1.7469. Min Act: -0.0000

Data Index: 1510296 (Python Code)

Max Activating Token Index: 14

Text #14

Max Range: 2.1883. Min Range: -2.1883

Max Act: 1.6480. Min Act: -0.0000

Data Index: 1543288 (Python Code)

Max Activating Token Index: 14

Text #15

Max Range: 2.1883. Min Range: -2.1883

Max Act: 1.6147. Min Act: -0.0000

Data Index: 1646767 (Python Code)

Max Activating Token Index: 128

Text #16

Max Range: 2.1883. Min Range: -2.1883

Max Act: 1.7217. Min Act: -0.0000

Data Index: 1542121 (Python Code)

Max Activating Token Index: 264

Text #17

Max Range: 2.1883. Min Range: -2.1883

Max Act: 1.7151. Min Act: -0.0000

Data Index: 1527003 (Python Code)

Max Activating Token Index: 62

Text #18

Max Range: 2.1883. Min Range: -2.1883

Max Act: 1.5290. Min Act: -0.0000

Data Index: 1541432 (Python Code)

Max Activating Token Index: 289

Text #19

Max Range: 2.1883. Min Range: -2.1883

Max Act: 1.7199. Min Act: -0.0000

Data Index: 1570200 (Python Code)

Max Activating Token Index: 23