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

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

Neuron 1474 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: 2.3103. Min Range: -2.3103

Max Act: 2.3103. Min Act: -0.0000

Data Index: 280581 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 2.3103. Min Range: -2.3103

Max Act: 2.2124. Min Act: -0.0000

Data Index: 1026802 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.8602. Min Act: -0.0000

Data Index: 176103 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.8884. Min Act: -0.0000

Data Index: 1154414 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.8182. Min Act: -0.0000

Data Index: 592 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.6147. Min Act: -0.0000

Data Index: 820522 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.6335. Min Act: -0.0000

Data Index: 285104 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.6090. Min Act: -0.0000

Data Index: 249742 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.6820. Min Act: -0.0000

Data Index: 286110 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.6647. Min Act: -0.0000

Data Index: 1292300 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.6742. Min Act: -0.0000

Data Index: 325135 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.6653. Min Act: -0.0000

Data Index: 668128 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.5644. Min Act: -0.0000

Data Index: 757023 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.6078. Min Act: -0.0000

Data Index: 1018198 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.5580. Min Act: -0.0000

Data Index: 771854 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.7098. Min Act: -0.0000

Data Index: 1346842 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.7172. Min Act: -0.0000

Data Index: 1305497 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.6535. Min Act: -0.0000

Data Index: 159074 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.5680. Min Act: -0.0000

Data Index: 877812 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 2.3103. Min Range: -2.3103

Max Act: 1.4859. Min Act: -0.0000

Data Index: 679859 (C4 (Web Text))

Max Activating Token Index: 665