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

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

Neuron 1244 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: 3.0075. Min Range: -3.0075

Max Act: 3.0075. Min Act: -0.0000

Data Index: 1123132 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 3.0075. Min Range: -3.0075

Max Act: 2.4341. Min Act: -0.0000

Data Index: 756711 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 3.0075. Min Range: -3.0075

Max Act: 2.2323. Min Act: -0.0000

Data Index: 986588 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 3.0075. Min Range: -3.0075

Max Act: 2.3627. Min Act: -0.0000

Data Index: 824372 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 3.0075. Min Range: -3.0075

Max Act: 2.0935. Min Act: -0.0000

Data Index: 145393 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 3.0075. Min Range: -3.0075

Max Act: 2.0441. Min Act: -0.0000

Data Index: 310119 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 3.0075. Min Range: -3.0075

Max Act: 2.0325. Min Act: -0.0000

Data Index: 1011011 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 3.0075. Min Range: -3.0075

Max Act: 1.8993. Min Act: -0.0000

Data Index: 483819 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 3.0075. Min Range: -3.0075

Max Act: 2.1000. Min Act: -0.0000

Data Index: 1232410 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 3.0075. Min Range: -3.0075

Max Act: 1.9404. Min Act: -0.0000

Data Index: 919603 (C4 (Web Text))

Max Activating Token Index: 313

Text #10

Max Range: 3.0075. Min Range: -3.0075

Max Act: 1.7842. Min Act: -0.0000

Data Index: 347916 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 3.0075. Min Range: -3.0075

Max Act: 1.9801. Min Act: -0.0000

Data Index: 733509 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 3.0075. Min Range: -3.0075

Max Act: 1.9501. Min Act: -0.0000

Data Index: 13529 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 3.0075. Min Range: -3.0075

Max Act: 1.7407. Min Act: -0.0000

Data Index: 1140424 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 3.0075. Min Range: -3.0075

Max Act: 1.7225. Min Act: -0.0000

Data Index: 468180 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 3.0075. Min Range: -3.0075

Max Act: 1.7075. Min Act: -0.0000

Data Index: 389966 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 3.0075. Min Range: -3.0075

Max Act: 1.8887. Min Act: -0.0000

Data Index: 1311987 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 3.0075. Min Range: -3.0075

Max Act: 1.7863. Min Act: -0.0000

Data Index: 1256562 (C4 (Web Text))

Max Activating Token Index: 346

Text #18

Max Range: 3.0075. Min Range: -3.0075

Max Act: 1.6923. Min Act: -0.0000

Data Index: 948998 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 3.0075. Min Range: -3.0075

Max Act: 2.0028. Min Act: -0.0000

Data Index: 1300573 (C4 (Web Text))

Max Activating Token Index: 927