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

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

Neuron 3452 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.8352. Min Act: -0.0000

Data Index: 319670 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 3.0129. Min Range: -3.0129

Max Act: 3.0129. Min Act: -0.0000

Data Index: 808983 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.5695. Min Act: -0.0000

Data Index: 526845 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.5348. Min Act: -0.0000

Data Index: 454344 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.5931. Min Act: -0.0000

Data Index: 308706 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.3547. Min Act: -0.0000

Data Index: 610211 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.3922. Min Act: -0.0000

Data Index: 1316287 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.2618. Min Act: -0.0000

Data Index: 287373 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.1260. Min Act: -0.0000

Data Index: 1132941 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.3569. Min Act: -0.0000

Data Index: 1045424 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.3026. Min Act: -0.0000

Data Index: 92803 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.1863. Min Act: -0.0000

Data Index: 674740 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.0818. Min Act: -0.0000

Data Index: 709502 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.1605. Min Act: -0.0000

Data Index: 813992 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.1606. Min Act: -0.0000

Data Index: 145711 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 3.0129. Min Range: -3.0129

Max Act: 1.9445. Min Act: -0.0000

Data Index: 269901 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.0265. Min Act: -0.0000

Data Index: 788021 (C4 (Web Text))

Max Activating Token Index: 575

Text #17

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.1328. Min Act: -0.0000

Data Index: 1228227 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 3.0129. Min Range: -3.0129

Max Act: 1.9947. Min Act: -0.0000

Data Index: 1114881 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 3.0129. Min Range: -3.0129

Max Act: 2.2083. Min Act: -0.0000

Data Index: 987287 (C4 (Web Text))

Max Activating Token Index: 31