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

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

Neuron 3388 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.7413. Min Act: -0.0000

Data Index: 25673 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.6655. Min Act: -0.0000

Data Index: 909589 (C4 (Web Text))

Max Activating Token Index: 210

Text #2

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5406. Min Act: -0.0000

Data Index: 551191 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5558. Min Act: -0.0000

Data Index: 505099 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5348. Min Act: -0.0000

Data Index: 331227 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5062. Min Act: -0.0000

Data Index: 726405 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.4901. Min Act: -0.0000

Data Index: 110472 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.4860. Min Act: -0.0000

Data Index: 374195 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1015541 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1152557 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.5798. Min Act: -0.0000

Data Index: 431882 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.4666. Min Act: -0.0000

Data Index: 30531 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.4810. Min Act: -0.0000

Data Index: 659632 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.4420. Min Act: -0.0000

Data Index: 274151 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.4827. Min Act: -0.0000

Data Index: 96256 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.4239. Min Act: -0.0000

Data Index: 717057 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.4166. Min Act: -0.0000

Data Index: 143391 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.4332. Min Act: -0.0000

Data Index: 622485 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.4311. Min Act: -0.0000

Data Index: 353060 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.7413. Min Range: -0.7413

Max Act: 0.4145. Min Act: -0.0000

Data Index: 415014 (C4 (Web Text))

Max Activating Token Index: 469