Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 652 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.7397. Min Act: -0.0001

Data Index: 856443 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.7068. Min Act: -0.0001

Data Index: 165487 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6279. Min Act: -0.0001

Data Index: 340638 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6593. Min Act: -0.0001

Data Index: 1172064 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6460. Min Act: -0.0001

Data Index: 586119 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5999. Min Act: -0.0001

Data Index: 920548 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5632. Min Act: -0.0001

Data Index: 629784 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6290. Min Act: -0.0001

Data Index: 319678 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5214. Min Act: -0.0001

Data Index: 925848 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5316. Min Act: -0.0001

Data Index: 605964 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5173. Min Act: -0.0001

Data Index: 361263 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5046. Min Act: -0.0001

Data Index: 868212 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5193. Min Act: -0.0001

Data Index: 814271 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5154. Min Act: -0.0001

Data Index: 939112 (C4 (Web Text))

Max Activating Token Index: 89

Text #14

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5130. Min Act: -0.0001

Data Index: 1264730 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5276. Min Act: -0.0001

Data Index: 1074541 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5084. Min Act: -0.0001

Data Index: 538293 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.4908. Min Act: -0.0001

Data Index: 709375 (C4 (Web Text))

Max Activating Token Index: 586

Text #18

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5276. Min Act: -0.0001

Data Index: 858611 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.4968. Min Act: -0.0001

Data Index: 699405 (C4 (Web Text))

Max Activating Token Index: 593