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

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

Neuron 3871 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: 1.5300. Min Range: -1.5300

Max Act: 1.5300. Min Act: -0.0000

Data Index: 1040207 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.4817. Min Act: -0.0000

Data Index: 1521287 (Python Code)

Max Activating Token Index: 799

Text #2

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.2968. Min Act: -0.0000

Data Index: 345527 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.1752. Min Act: -0.0000

Data Index: 333225 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.3048. Min Act: -0.0000

Data Index: 956545 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.1958. Min Act: -0.0000

Data Index: 1420892 (Python Code)

Max Activating Token Index: 178

Text #6

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.3101. Min Act: -0.0000

Data Index: 1367122 (Python Code)

Max Activating Token Index: 36

Text #7

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.3172. Min Act: -0.0000

Data Index: 859863 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.2456. Min Act: -0.0000

Data Index: 1232907 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.2461. Min Act: -0.0000

Data Index: 1588080 (Python Code)

Max Activating Token Index: 464

Text #10

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.1668. Min Act: -0.0000

Data Index: 1622895 (Python Code)

Max Activating Token Index: 734

Text #11

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.1913. Min Act: -0.0000

Data Index: 1379329 (Python Code)

Max Activating Token Index: 607

Text #12

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.0824. Min Act: -0.0000

Data Index: 573389 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.0954. Min Act: -0.0000

Data Index: 1051707 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.0697. Min Act: -0.0000

Data Index: 1564998 (Python Code)

Max Activating Token Index: 597

Text #15

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.0318. Min Act: -0.0000

Data Index: 1127793 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.0527. Min Act: -0.0000

Data Index: 1327325 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.0645. Min Act: -0.0000

Data Index: 197114 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.0550. Min Act: -0.0000

Data Index: 1426929 (Python Code)

Max Activating Token Index: 826

Text #19

Max Range: 1.5300. Min Range: -1.5300

Max Act: 1.0515. Min Act: -0.0000

Data Index: 1536722 (Python Code)

Max Activating Token Index: 582