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

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

Neuron 273 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.7803. Min Act: -0.0001

Data Index: 159488 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.8029. Min Act: -0.0001

Data Index: 1070334 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.7926. Min Act: -0.0001

Data Index: 1292255 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.7628. Min Act: -0.0001

Data Index: 587197 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.7571. Min Act: -0.0001

Data Index: 553034 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.7303. Min Act: -0.0001

Data Index: 1302731 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.7064. Min Act: -0.0001

Data Index: 1291227 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.7181. Min Act: -0.0001

Data Index: 251251 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.7369. Min Act: -0.0001

Data Index: 860202 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.6841. Min Act: -0.0001

Data Index: 1016704 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.7008. Min Act: -0.0001

Data Index: 1082358 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.6983. Min Act: -0.0001

Data Index: 155052 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.6898. Min Act: -0.0001

Data Index: 752520 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.6687. Min Act: -0.0001

Data Index: 609394 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.7143. Min Act: -0.0001

Data Index: 1142611 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.6454. Min Act: -0.0001

Data Index: 796912 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.7066. Min Act: -0.0001

Data Index: 91191 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.6834. Min Act: -0.0001

Data Index: 863579 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.6807. Min Act: -0.0001

Data Index: 1107712 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.8029. Min Range: -0.8029

Max Act: 0.6951. Min Act: -0.0001

Data Index: 324844 (C4 (Web Text))

Max Activating Token Index: 557