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

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

Neuron 1566 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1289272 (C4 (Web Text))

Max Activating Token Index: 793

Text #1

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5792. Min Act: -0.0000

Data Index: 279504 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.6041. Min Act: -0.0000

Data Index: 40652 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1182714 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1249043 (C4 (Web Text))

Max Activating Token Index: 504

Text #5

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4825. Min Act: -0.0000

Data Index: 318196 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5148. Min Act: -0.0000

Data Index: 478668 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4470. Min Act: -0.0000

Data Index: 892093 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4353. Min Act: -0.0000

Data Index: 521554 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4260. Min Act: -0.0000

Data Index: 673963 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4436. Min Act: -0.0000

Data Index: 502741 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4707. Min Act: -0.0000

Data Index: 1147827 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4097. Min Act: -0.0000

Data Index: 220188 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4045. Min Act: -0.0000

Data Index: 192183 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4069. Min Act: -0.0000

Data Index: 855047 (C4 (Web Text))

Max Activating Token Index: 594

Text #15

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4020. Min Act: -0.0000

Data Index: 55499 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4050. Min Act: -0.0000

Data Index: 856039 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.3815. Min Act: -0.0000

Data Index: 1003778 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.3671. Min Act: -0.0000

Data Index: 307535 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4297. Min Act: -0.0000

Data Index: 856798 (C4 (Web Text))

Max Activating Token Index: 411