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

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

Neuron 4704 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: 1.6846. Min Range: -1.6846

Max Act: 1.6846. Min Act: -0.0000

Data Index: 526621 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.5771. Min Act: -0.0000

Data Index: 354882 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.4866. Min Act: -0.0000

Data Index: 1220418 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.4897. Min Act: -0.0000

Data Index: 644206 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.5598. Min Act: -0.0000

Data Index: 620544 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.4867. Min Act: -0.0000

Data Index: 1354291 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.3594. Min Act: -0.0000

Data Index: 802610 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.3758. Min Act: -0.0000

Data Index: 1328290 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.3529. Min Act: -0.0000

Data Index: 964606 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.5048. Min Act: -0.0000

Data Index: 354680 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.3337. Min Act: -0.0000

Data Index: 483061 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.3111. Min Act: -0.0000

Data Index: 673638 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.3975. Min Act: -0.0000

Data Index: 1270722 (C4 (Web Text))

Max Activating Token Index: 490

Text #13

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.3077. Min Act: 0.0000

Data Index: 220189 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.2170. Min Act: -0.0000

Data Index: 1323797 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.1918. Min Act: -0.0000

Data Index: 222315 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.2502. Min Act: -0.0000

Data Index: 55553 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.1751. Min Act: -0.0000

Data Index: 84246 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.3127. Min Act: -0.0000

Data Index: 497076 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 1.6846. Min Range: -1.6846

Max Act: 1.2107. Min Act: 0.0000

Data Index: 1163585 (C4 (Web Text))

Max Activating Token Index: 868