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

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

Neuron 4940 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.3899. Min Act: -0.0000

Data Index: 362065 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.3357. Min Act: -0.0000

Data Index: 197036 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.3096. Min Act: -0.0000

Data Index: 702408 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.3888. Min Act: -0.0000

Data Index: 1072229 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.3846. Min Act: -0.0000

Data Index: 1076240 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.3621. Min Act: -0.0000

Data Index: 439826 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.2863. Min Act: -0.0000

Data Index: 918361 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.2208. Min Act: -0.0000

Data Index: 1257487 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.3554. Min Act: -0.0000

Data Index: 492220 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.2536. Min Act: -0.0000

Data Index: 1110185 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.3460. Min Act: -0.0000

Data Index: 334414 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.3074. Min Act: -0.0000

Data Index: 487793 (C4 (Web Text))

Max Activating Token Index: 62

Text #12

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.1320. Min Act: -0.0000

Data Index: 871698 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.3429. Min Act: -0.0000

Data Index: 145086 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.2244. Min Act: -0.0000

Data Index: 224576 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.2175. Min Act: -0.0000

Data Index: 466630 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.2124. Min Act: -0.0000

Data Index: 616454 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.1449. Min Act: -0.0000

Data Index: 1212489 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.1802. Min Act: -0.0000

Data Index: 1044919 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 1.3899. Min Range: -1.3899

Max Act: 1.2108. Min Act: -0.0000

Data Index: 1077805 (C4 (Web Text))

Max Activating Token Index: 902