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

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

Neuron 4439 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.4116. Min Act: -0.0003

Data Index: 1069677 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3469. Min Act: -0.0003

Data Index: 527591 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3529. Min Act: -0.0003

Data Index: 454368 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3512. Min Act: -0.0003

Data Index: 303200 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3418. Min Act: -0.0003

Data Index: 1306678 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3379. Min Act: -0.0003

Data Index: 1005058 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3386. Min Act: -0.0003

Data Index: 733061 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3308. Min Act: -0.0003

Data Index: 780958 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3267. Min Act: -0.0002

Data Index: 44666 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3252. Min Act: -0.0003

Data Index: 1017573 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3184. Min Act: -0.0002

Data Index: 584471 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3120. Min Act: -0.0003

Data Index: 540998 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3094. Min Act: -0.0003

Data Index: 769805 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3007. Min Act: -0.0003

Data Index: 192986 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.2984. Min Act: -0.0003

Data Index: 525129 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.3078. Min Act: -0.0003

Data Index: 161825 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.2958. Min Act: -0.0003

Data Index: 249255 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.2951. Min Act: -0.0003

Data Index: 783206 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.2950. Min Act: -0.0003

Data Index: 857521 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.4116. Min Range: -0.4116

Max Act: 0.2936. Min Act: -0.0003

Data Index: 1124619 (C4 (Web Text))

Max Activating Token Index: 59