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

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

Neuron 665 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9925. Min Range: -5.9925

Max Act: 5.9629. Min Act: -0.0000

Data Index: 1053673 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 5.9925. Min Range: -5.9925

Max Act: 5.9925. Min Act: -0.0000

Data Index: 491305 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 5.9925. Min Range: -5.9925

Max Act: 4.9185. Min Act: -0.0000

Data Index: 245102 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 5.9925. Min Range: -5.9925

Max Act: 5.2740. Min Act: -0.0000

Data Index: 392591 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 5.9925. Min Range: -5.9925

Max Act: 5.0583. Min Act: -0.0000

Data Index: 1288241 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 5.9925. Min Range: -5.9925

Max Act: 4.8790. Min Act: -0.0000

Data Index: 489227 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 5.9925. Min Range: -5.9925

Max Act: 4.8632. Min Act: -0.0000

Data Index: 70432 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 5.9925. Min Range: -5.9925

Max Act: 4.6698. Min Act: -0.0000

Data Index: 1030015 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 5.9925. Min Range: -5.9925

Max Act: 4.8626. Min Act: -0.0000

Data Index: 259678 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 5.9925. Min Range: -5.9925

Max Act: 5.2620. Min Act: -0.0000

Data Index: 998821 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 5.9925. Min Range: -5.9925

Max Act: 4.6860. Min Act: -0.0000

Data Index: 1254161 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 5.9925. Min Range: -5.9925

Max Act: 4.3615. Min Act: -0.0000

Data Index: 487227 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 5.9925. Min Range: -5.9925

Max Act: 4.8699. Min Act: -0.0000

Data Index: 541984 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 5.9925. Min Range: -5.9925

Max Act: 4.4829. Min Act: -0.0000

Data Index: 280502 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 5.9925. Min Range: -5.9925

Max Act: 4.5580. Min Act: -0.0000

Data Index: 965187 (C4 (Web Text))

Max Activating Token Index: 484

Text #15

Max Range: 5.9925. Min Range: -5.9925

Max Act: 4.3134. Min Act: -0.0000

Data Index: 284068 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 5.9925. Min Range: -5.9925

Max Act: 4.5039. Min Act: -0.0000

Data Index: 1285514 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 5.9925. Min Range: -5.9925

Max Act: 3.8966. Min Act: -0.0000

Data Index: 323757 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 5.9925. Min Range: -5.9925

Max Act: 4.1526. Min Act: -0.0000

Data Index: 298731 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 5.9925. Min Range: -5.9925

Max Act: 4.1589. Min Act: -0.0000

Data Index: 720986 (C4 (Web Text))

Max Activating Token Index: 1023