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

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

Neuron 3779 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.6987. Min Act: -0.0001

Data Index: 289412 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.5827. Min Act: -0.0001

Data Index: 717003 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.5604. Min Act: -0.0001

Data Index: 379780 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.3945. Min Act: -0.0001

Data Index: 111584 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.6412. Min Act: -0.0001

Data Index: 1021490 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.3992. Min Act: -0.0001

Data Index: 900071 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.4129. Min Act: -0.0001

Data Index: 548149 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.4756. Min Act: -0.0001

Data Index: 80097 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.4812. Min Act: -0.0001

Data Index: 1326034 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.2288. Min Act: -0.0001

Data Index: 885955 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.2730. Min Act: -0.0001

Data Index: 1237834 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.3152. Min Act: -0.0001

Data Index: 573107 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.2614. Min Act: -0.0001

Data Index: 270336 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.3880. Min Act: -0.0001

Data Index: 365923 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.3140. Min Act: -0.0001

Data Index: 314878 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.2447. Min Act: -0.0001

Data Index: 1314036 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.2713. Min Act: -0.0001

Data Index: 354366 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.2585. Min Act: -0.0001

Data Index: 1308444 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.0543. Min Act: -0.0001

Data Index: 607783 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 1.6987. Min Range: -1.6987

Max Act: 1.1710. Min Act: -0.0001

Data Index: 1107774 (C4 (Web Text))

Max Activating Token Index: 84