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

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

Neuron 5162 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.8145. Min Act: -0.0000

Data Index: 352820 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.5564. Min Act: -0.0000

Data Index: 102605 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.6001. Min Act: -0.0000

Data Index: 460328 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.5918. Min Act: -0.0000

Data Index: 490107 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.5006. Min Act: -0.0000

Data Index: 61130 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.5626. Min Act: -0.0000

Data Index: 121770 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.4817. Min Act: -0.0000

Data Index: 1165316 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.4966. Min Act: -0.0000

Data Index: 910835 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.3935. Min Act: -0.0000

Data Index: 208894 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.4626. Min Act: -0.0000

Data Index: 1332093 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.4424. Min Act: -0.0000

Data Index: 301238 (C4 (Web Text))

Max Activating Token Index: 203

Text #11

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.5375. Min Act: -0.0000

Data Index: 537243 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.3972. Min Act: -0.0000

Data Index: 517346 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.3893. Min Act: -0.0000

Data Index: 296116 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.3764. Min Act: -0.0000

Data Index: 1241948 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.3638. Min Act: -0.0000

Data Index: 560793 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.2954. Min Act: -0.0000

Data Index: 428259 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.2816. Min Act: -0.0000

Data Index: 698858 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.2482. Min Act: -0.0000

Data Index: 1085491 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 1.8145. Min Range: -1.8145

Max Act: 1.2609. Min Act: -0.0000

Data Index: 1165501 (C4 (Web Text))

Max Activating Token Index: 813