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

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

Neuron 3829 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: 2.0210. Min Range: -2.0210

Max Act: 2.0210. Min Act: -0.0000

Data Index: 48830 (C4 (Web Text))

Max Activating Token Index: 738

Text #1

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.9070. Min Act: -0.0000

Data Index: 653286 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.8138. Min Act: -0.0000

Data Index: 1146127 (C4 (Web Text))

Max Activating Token Index: 119

Text #3

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.7801. Min Act: -0.0000

Data Index: 261866 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.7041. Min Act: -0.0000

Data Index: 503926 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.6671. Min Act: -0.0000

Data Index: 739872 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.5745. Min Act: -0.0000

Data Index: 79615 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.5574. Min Act: -0.0000

Data Index: 807616 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.5285. Min Act: -0.0000

Data Index: 456843 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.5066. Min Act: -0.0000

Data Index: 282426 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.5077. Min Act: -0.0000

Data Index: 306039 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.4180. Min Act: -0.0000

Data Index: 158923 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.3231. Min Act: -0.0000

Data Index: 145036 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.4120. Min Act: -0.0000

Data Index: 814355 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.3931. Min Act: -0.0000

Data Index: 341962 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.3038. Min Act: -0.0000

Data Index: 1252596 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.3809. Min Act: -0.0000

Data Index: 160255 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.3815. Min Act: -0.0000

Data Index: 459326 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.3722. Min Act: -0.0000

Data Index: 633205 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 2.0210. Min Range: -2.0210

Max Act: 1.4229. Min Act: -0.0000

Data Index: 508687 (C4 (Web Text))

Max Activating Token Index: 754