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

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

Neuron 3302 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.8940. Min Act: -0.0001

Data Index: 564305 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.8622. Min Act: -0.0001

Data Index: 641997 (C4 (Web Text))

Max Activating Token Index: 698

Text #2

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7044. Min Act: -0.0001

Data Index: 972947 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.7237. Min Act: -0.0001

Data Index: 237391 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.6030. Min Act: -0.0001

Data Index: 474364 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.5915. Min Act: -0.0001

Data Index: 968927 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1307140 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.5323. Min Act: -0.0001

Data Index: 1133917 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.4842. Min Act: -0.0001

Data Index: 64388 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.4842. Min Act: -0.0001

Data Index: 828791 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.3996. Min Act: -0.0001

Data Index: 733403 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.4453. Min Act: -0.0001

Data Index: 459448 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.4681. Min Act: -0.0001

Data Index: 799585 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.4473. Min Act: -0.0001

Data Index: 1232734 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.4168. Min Act: -0.0001

Data Index: 1309766 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.4325. Min Act: -0.0001

Data Index: 1181859 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.4017. Min Act: -0.0001

Data Index: 1324667 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.4167. Min Act: -0.0000

Data Index: 991962 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1157586 (C4 (Web Text))

Max Activating Token Index: 300

Text #19

Max Range: 0.8940. Min Range: -0.8940

Max Act: 0.4082. Min Act: -0.0001

Data Index: 363751 (C4 (Web Text))

Max Activating Token Index: 823