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

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

Neuron 339 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.4280. Min Act: -0.0001

Data Index: 1319283 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3993. Min Act: -0.0001

Data Index: 1188179 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3254. Min Act: -0.0001

Data Index: 896500 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3268. Min Act: -0.0001

Data Index: 481840 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3318. Min Act: -0.0001

Data Index: 620051 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3096. Min Act: -0.0001

Data Index: 723355 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3324. Min Act: -0.0001

Data Index: 1495170 (Python Code)

Max Activating Token Index: 965

Text #7

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3193. Min Act: -0.0001

Data Index: 756745 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2940. Min Act: -0.0001

Data Index: 357109 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2797. Min Act: -0.0001

Data Index: 1208949 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3133. Min Act: -0.0001

Data Index: 997887 (C4 (Web Text))

Max Activating Token Index: 752

Text #11

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2976. Min Act: -0.0001

Data Index: 1040419 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3086. Min Act: -0.0001

Data Index: 535993 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2948. Min Act: -0.0001

Data Index: 553941 (C4 (Web Text))

Max Activating Token Index: 694

Text #14

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2949. Min Act: -0.0001

Data Index: 825296 (C4 (Web Text))

Max Activating Token Index: 190

Text #15

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.3025. Min Act: -0.0001

Data Index: 751547 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2830. Min Act: -0.0001

Data Index: 504681 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2712. Min Act: -0.0001

Data Index: 1259693 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2825. Min Act: -0.0001

Data Index: 313125 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.4280. Min Range: -0.4280

Max Act: 0.2814. Min Act: -0.0001

Data Index: 1249716 (C4 (Web Text))

Max Activating Token Index: 808