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

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

Neuron 3250 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.8992. Min Act: -0.0000

Data Index: 583844 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.7051. Min Act: -0.0000

Data Index: 61227 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.5685. Min Act: -0.0000

Data Index: 625152 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.5764. Min Act: -0.0000

Data Index: 64185 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.4083. Min Act: -0.0000

Data Index: 1127737 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.4727. Min Act: -0.0000

Data Index: 1167237 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.5557. Min Act: -0.0000

Data Index: 387158 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.4097. Min Act: -0.0000

Data Index: 285967 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.3912. Min Act: -0.0001

Data Index: 1592532 (Python Code)

Max Activating Token Index: 516

Text #9

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.4131. Min Act: -0.0000

Data Index: 96232 (C4 (Web Text))

Max Activating Token Index: 374

Text #10

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.3692. Min Act: -0.0000

Data Index: 1197921 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.3599. Min Act: -0.0000

Data Index: 49974 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.4252. Min Act: -0.0000

Data Index: 1089943 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.4591. Min Act: -0.0001

Data Index: 1545339 (Python Code)

Max Activating Token Index: 628

Text #14

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.4169. Min Act: -0.0000

Data Index: 1190028 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.3608. Min Act: -0.0000

Data Index: 696536 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.3930. Min Act: -0.0000

Data Index: 1032737 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.3573. Min Act: -0.0000

Data Index: 355654 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.3225. Min Act: -0.0000

Data Index: 428749 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 1.8992. Min Range: -1.8992

Max Act: 1.4071. Min Act: -0.0001

Data Index: 1506333 (Python Code)

Max Activating Token Index: 833