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

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

Neuron 2631 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: 1.9521. Min Range: -1.9521

Max Act: 1.9521. Min Act: -0.0000

Data Index: 1405508 (Python Code)

Max Activating Token Index: 466

Text #1

Max Range: 1.9521. Min Range: -1.9521

Max Act: 1.2511. Min Act: -0.0000

Data Index: 319732 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 1.9521. Min Range: -1.9521

Max Act: 1.2847. Min Act: -0.0000

Data Index: 1255179 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 1.9521. Min Range: -1.9521

Max Act: 1.2188. Min Act: -0.0000

Data Index: 814117 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 1.9521. Min Range: -1.9521

Max Act: 1.1890. Min Act: -0.0000

Data Index: 1156787 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 1.9521. Min Range: -1.9521

Max Act: 1.1089. Min Act: -0.0000

Data Index: 1182979 (C4 (Web Text))

Max Activating Token Index: 752

Text #6

Max Range: 1.9521. Min Range: -1.9521

Max Act: 1.0837. Min Act: -0.0000

Data Index: 335812 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 1.9521. Min Range: -1.9521

Max Act: 1.0438. Min Act: -0.0000

Data Index: 116771 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 1.9521. Min Range: -1.9521

Max Act: 1.0172. Min Act: -0.0000

Data Index: 109629 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 1.9521. Min Range: -1.9521

Max Act: 1.0294. Min Act: -0.0000

Data Index: 798569 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 1.9521. Min Range: -1.9521

Max Act: 0.9211. Min Act: -0.0000

Data Index: 1656807 (Python Code)

Max Activating Token Index: 456

Text #11

Max Range: 1.9521. Min Range: -1.9521

Max Act: 0.9997. Min Act: -0.0000

Data Index: 167345 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 1.9521. Min Range: -1.9521

Max Act: 1.0175. Min Act: -0.0000

Data Index: 1443409 (Python Code)

Max Activating Token Index: 892

Text #13

Max Range: 1.9521. Min Range: -1.9521

Max Act: 0.9482. Min Act: -0.0000

Data Index: 1279330 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 1.9521. Min Range: -1.9521

Max Act: 1.0354. Min Act: -0.0000

Data Index: 737425 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.9521. Min Range: -1.9521

Max Act: 0.9469. Min Act: -0.0000

Data Index: 1480361 (Python Code)

Max Activating Token Index: 939

Text #16

Max Range: 1.9521. Min Range: -1.9521

Max Act: 0.9386. Min Act: -0.0000

Data Index: 1169549 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 1.9521. Min Range: -1.9521

Max Act: 0.9038. Min Act: -0.0000

Data Index: 88195 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 1.9521. Min Range: -1.9521

Max Act: 0.8866. Min Act: -0.0000

Data Index: 787303 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 1.9521. Min Range: -1.9521

Max Act: 1.0158. Min Act: -0.0000

Data Index: 1395173 (Python Code)

Max Activating Token Index: 433