Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4717 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0424. Min Range: -1.0424

Max Act: 1.0424. Min Act: -0.0000

Data Index: 933733 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 1.0424. Min Range: -1.0424

Max Act: 1.0285. Min Act: -0.0000

Data Index: 578440 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1549221 (Python Code)

Max Activating Token Index: 61

Text #3

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.7645. Min Act: -0.0000

Data Index: 738228 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.6920. Min Act: -0.0000

Data Index: 1623254 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1545105 (Python Code)

Max Activating Token Index: 21

Text #6

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.7007. Min Act: -0.0000

Data Index: 1374721 (Python Code)

Max Activating Token Index: 1015

Text #7

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.6580. Min Act: -0.0000

Data Index: 1350303 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1593554 (Python Code)

Max Activating Token Index: 204

Text #9

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.6494. Min Act: -0.0000

Data Index: 125339 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.6411. Min Act: -0.0000

Data Index: 768073 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1382019 (Python Code)

Max Activating Token Index: 768

Text #12

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1538708 (Python Code)

Max Activating Token Index: 400

Text #13

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.5484. Min Act: -0.0000

Data Index: 89531 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1618580 (Python Code)

Max Activating Token Index: 67

Text #15

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.5432. Min Act: -0.0000

Data Index: 1450975 (Python Code)

Max Activating Token Index: 21

Text #16

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.5524. Min Act: -0.0000

Data Index: 1425499 (Python Code)

Max Activating Token Index: 529

Text #17

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1435531 (Python Code)

Max Activating Token Index: 195

Text #18

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1598130 (Python Code)

Max Activating Token Index: 186

Text #19

Max Range: 1.0424. Min Range: -1.0424

Max Act: 0.5515. Min Act: -0.0000

Data Index: 1542823 (Python Code)

Max Activating Token Index: 771