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

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

Neuron 3276 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.2880. Min Range: -6.2880

Max Act: 6.1743. Min Act: -0.0000

Data Index: 5019 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 6.2880. Min Range: -6.2880

Max Act: 6.2880. Min Act: -0.0000

Data Index: 237724 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 6.2880. Min Range: -6.2880

Max Act: 6.0475. Min Act: -0.0000

Data Index: 645467 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 6.2880. Min Range: -6.2880

Max Act: 6.0017. Min Act: -0.0000

Data Index: 680961 (C4 (Web Text))

Max Activating Token Index: 454

Text #4

Max Range: 6.2880. Min Range: -6.2880

Max Act: 5.8542. Min Act: -0.0000

Data Index: 495499 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 6.2880. Min Range: -6.2880

Max Act: 5.3641. Min Act: -0.0000

Data Index: 40139 (C4 (Web Text))

Max Activating Token Index: 549

Text #6

Max Range: 6.2880. Min Range: -6.2880

Max Act: 5.3546. Min Act: -0.0000

Data Index: 1005246 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 6.2880. Min Range: -6.2880

Max Act: 4.9717. Min Act: -0.0000

Data Index: 652613 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 6.2880. Min Range: -6.2880

Max Act: 5.1131. Min Act: -0.0000

Data Index: 851504 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 6.2880. Min Range: -6.2880

Max Act: 4.8640. Min Act: -0.0000

Data Index: 1045574 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 6.2880. Min Range: -6.2880

Max Act: 5.1321. Min Act: -0.0000

Data Index: 1226093 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 6.2880. Min Range: -6.2880

Max Act: 4.6552. Min Act: -0.0000

Data Index: 1249365 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 6.2880. Min Range: -6.2880

Max Act: 5.0401. Min Act: -0.0000

Data Index: 980453 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 6.2880. Min Range: -6.2880

Max Act: 5.2264. Min Act: -0.0000

Data Index: 173733 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 6.2880. Min Range: -6.2880

Max Act: 4.9023. Min Act: -0.0000

Data Index: 1317430 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 6.2880. Min Range: -6.2880

Max Act: 4.6506. Min Act: -0.0000

Data Index: 530881 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 6.2880. Min Range: -6.2880

Max Act: 4.7831. Min Act: -0.0000

Data Index: 121783 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 6.2880. Min Range: -6.2880

Max Act: 4.3992. Min Act: -0.0000

Data Index: 723986 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 6.2880. Min Range: -6.2880

Max Act: 4.7450. Min Act: 0.0000

Data Index: 156524 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 6.2880. Min Range: -6.2880

Max Act: 5.2862. Min Act: -0.0000

Data Index: 1291224 (C4 (Web Text))

Max Activating Token Index: 988