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

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

Neuron 5667 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3915. Min Range: -2.3915

Max Act: 2.3915. Min Act: -0.0000

Data Index: 1356676 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 2.3915. Min Range: -2.3915

Max Act: 2.1780. Min Act: -0.0000

Data Index: 1328934 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 2.3915. Min Range: -2.3915

Max Act: 2.0703. Min Act: -0.0000

Data Index: 629043 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 2.3915. Min Range: -2.3915

Max Act: 2.0465. Min Act: -0.0000

Data Index: 456581 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 2.3915. Min Range: -2.3915

Max Act: 1.8285. Min Act: -0.0000

Data Index: 1268055 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 2.3915. Min Range: -2.3915

Max Act: 1.8821. Min Act: -0.0000

Data Index: 722113 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 2.3915. Min Range: -2.3915

Max Act: 1.8760. Min Act: -0.0000

Data Index: 1283381 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 2.3915. Min Range: -2.3915

Max Act: 1.8211. Min Act: -0.0000

Data Index: 684874 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 2.3915. Min Range: -2.3915

Max Act: 1.8075. Min Act: -0.0000

Data Index: 780366 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 2.3915. Min Range: -2.3915

Max Act: 1.9070. Min Act: -0.0000

Data Index: 396460 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 2.3915. Min Range: -2.3915

Max Act: 1.6670. Min Act: -0.0000

Data Index: 45463 (C4 (Web Text))

Max Activating Token Index: 430

Text #11

Max Range: 2.3915. Min Range: -2.3915

Max Act: 1.6541. Min Act: -0.0000

Data Index: 49322 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 2.3915. Min Range: -2.3915

Max Act: 1.8299. Min Act: -0.0000

Data Index: 216146 (C4 (Web Text))

Max Activating Token Index: 434

Text #13

Max Range: 2.3915. Min Range: -2.3915

Max Act: 1.7184. Min Act: -0.0000

Data Index: 865966 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 2.3915. Min Range: -2.3915

Max Act: 1.7118. Min Act: -0.0000

Data Index: 1197583 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 2.3915. Min Range: -2.3915

Max Act: 1.6951. Min Act: -0.0000

Data Index: 456517 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 2.3915. Min Range: -2.3915

Max Act: 1.6794. Min Act: -0.0000

Data Index: 678032 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 2.3915. Min Range: -2.3915

Max Act: 1.6833. Min Act: -0.0000

Data Index: 927634 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 2.3915. Min Range: -2.3915

Max Act: 1.6814. Min Act: -0.0000

Data Index: 63470 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 2.3915. Min Range: -2.3915

Max Act: 1.7642. Min Act: -0.0000

Data Index: 680897 (C4 (Web Text))

Max Activating Token Index: 331