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

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

Neuron 4322 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2204. Min Range: -1.2204

Max Act: 1.2204. Min Act: -0.0000

Data Index: 1039164 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.9511. Min Act: -0.0000

Data Index: 448383 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.8458. Min Act: -0.0000

Data Index: 531556 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.8651. Min Act: -0.0000

Data Index: 167130 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.7498. Min Act: -0.0000

Data Index: 693749 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.6650. Min Act: -0.0000

Data Index: 863373 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.7463. Min Act: -0.0000

Data Index: 136266 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1015993 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.6971. Min Act: -0.0000

Data Index: 85421 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.6966. Min Act: -0.0000

Data Index: 630458 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1355257 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.6662. Min Act: -0.0000

Data Index: 441456 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1244207 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1053918 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.5101. Min Act: -0.0000

Data Index: 425829 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.6022. Min Act: -0.0000

Data Index: 1095794 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.6066. Min Act: -0.0000

Data Index: 977334 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.6207. Min Act: -0.0000

Data Index: 413227 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.5886. Min Act: -0.0000

Data Index: 31898 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 1.2204. Min Range: -1.2204

Max Act: 0.5985. Min Act: -0.0000

Data Index: 296126 (C4 (Web Text))

Max Activating Token Index: 209