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

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

Neuron 2168 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: 3.7906. Min Range: -3.7906

Max Act: 3.7906. Min Act: -0.0000

Data Index: 204732 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.7667. Min Act: -0.0000

Data Index: 277051 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.6836. Min Act: -0.0000

Data Index: 591539 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.4949. Min Act: -0.0000

Data Index: 579826 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.3782. Min Act: -0.0000

Data Index: 708876 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 3.7906. Min Range: -3.7906

Max Act: 3.0374. Min Act: -0.0000

Data Index: 1233170 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 3.7906. Min Range: -3.7906

Max Act: 2.5048. Min Act: -0.0000

Data Index: 477566 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 3.7906. Min Range: -3.7906

Max Act: 2.5976. Min Act: -0.0000

Data Index: 1212158 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 3.7906. Min Range: -3.7906

Max Act: 2.4182. Min Act: -0.0000

Data Index: 629524 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 3.7906. Min Range: -3.7906

Max Act: 2.5730. Min Act: -0.0000

Data Index: 229259 (C4 (Web Text))

Max Activating Token Index: 635

Text #10

Max Range: 3.7906. Min Range: -3.7906

Max Act: 2.4021. Min Act: -0.0000

Data Index: 1134621 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 3.7906. Min Range: -3.7906

Max Act: 2.2674. Min Act: -0.0000

Data Index: 816995 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 3.7906. Min Range: -3.7906

Max Act: 2.2001. Min Act: -0.0000

Data Index: 1357358 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 3.7906. Min Range: -3.7906

Max Act: 2.5022. Min Act: -0.0000

Data Index: 254265 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 3.7906. Min Range: -3.7906

Max Act: 2.0956. Min Act: -0.0000

Data Index: 1039351 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 3.7906. Min Range: -3.7906

Max Act: 1.8769. Min Act: -0.0000

Data Index: 445132 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 3.7906. Min Range: -3.7906

Max Act: 1.9810. Min Act: -0.0000

Data Index: 1532502 (Python Code)

Max Activating Token Index: 163

Text #17

Max Range: 3.7906. Min Range: -3.7906

Max Act: 2.0520. Min Act: -0.0000

Data Index: 462615 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 3.7906. Min Range: -3.7906

Max Act: 2.0651. Min Act: -0.0000

Data Index: 1614311 (Python Code)

Max Activating Token Index: 324

Text #19

Max Range: 3.7906. Min Range: -3.7906

Max Act: 1.8966. Min Act: -0.0000

Data Index: 1008523 (C4 (Web Text))

Max Activating Token Index: 531