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

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

Neuron 5630 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.8426. Min Act: -0.0002

Data Index: 616882 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.8232. Min Act: -0.0002

Data Index: 859918 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.8106. Min Act: -0.0002

Data Index: 630992 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.8060. Min Act: -0.0002

Data Index: 1148063 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7975. Min Act: -0.0002

Data Index: 571124 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7958. Min Act: -0.0002

Data Index: 766258 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.8004. Min Act: -0.0002

Data Index: 165955 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7972. Min Act: -0.0002

Data Index: 720796 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.8005. Min Act: -0.0002

Data Index: 133084 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7908. Min Act: -0.0002

Data Index: 347276 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7648. Min Act: -0.0002

Data Index: 652732 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7689. Min Act: -0.0002

Data Index: 843932 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7643. Min Act: -0.0002

Data Index: 1431634 (Python Code)

Max Activating Token Index: 308

Text #13

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7748. Min Act: -0.0002

Data Index: 1085116 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7608. Min Act: -0.0002

Data Index: 1143536 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7494. Min Act: -0.0002

Data Index: 809465 (C4 (Web Text))

Max Activating Token Index: 159

Text #16

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7623. Min Act: -0.0002

Data Index: 925464 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7607. Min Act: -0.0002

Data Index: 429268 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7419. Min Act: -0.0002

Data Index: 462807 (C4 (Web Text))

Max Activating Token Index: 526

Text #19

Max Range: 0.8426. Min Range: -0.8426

Max Act: 0.7479. Min Act: -0.0002

Data Index: 1264966 (C4 (Web Text))

Max Activating Token Index: 15