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

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

Neuron 4816 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.5892. Min Act: -0.0000

Data Index: 106198 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4923. Min Act: -0.0000

Data Index: 1359500 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.5050. Min Act: -0.0000

Data Index: 836410 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4777. Min Act: -0.0000

Data Index: 136103 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4932. Min Act: -0.0000

Data Index: 899348 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4818. Min Act: -0.0000

Data Index: 683881 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4356. Min Act: -0.0000

Data Index: 132851 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4143. Min Act: -0.0000

Data Index: 458884 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4198. Min Act: -0.0000

Data Index: 975099 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4032. Min Act: -0.0000

Data Index: 782405 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1025589 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4062. Min Act: -0.0000

Data Index: 421747 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.3903. Min Act: -0.0000

Data Index: 839972 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.3590. Min Act: -0.0000

Data Index: 1239435 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1172307 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.3763. Min Act: -0.0000

Data Index: 238799 (C4 (Web Text))

Max Activating Token Index: 179

Text #16

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.3684. Min Act: -0.0000

Data Index: 565834 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.3852. Min Act: -0.0000

Data Index: 1337371 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.3861. Min Act: -0.0000

Data Index: 622762 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.5892. Min Range: -0.5892

Max Act: 0.3509. Min Act: -0.0000

Data Index: 487968 (C4 (Web Text))

Max Activating Token Index: 951