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

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

Neuron 3711 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3628. Min Act: -0.0000

Data Index: 1290991 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3436. Min Act: -0.0000

Data Index: 29534 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1263499 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3357. Min Act: -0.0000

Data Index: 882361 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1346117 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3440. Min Act: -0.0000

Data Index: 1322350 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1195413 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3006. Min Act: -0.0000

Data Index: 844431 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3222. Min Act: -0.0000

Data Index: 640899 (C4 (Web Text))

Max Activating Token Index: 397

Text #9

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3106. Min Act: -0.0000

Data Index: 1182899 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1001873 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3085. Min Act: -0.0000

Data Index: 638054 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3085. Min Act: -0.0000

Data Index: 676968 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2880. Min Act: -0.0000

Data Index: 543585 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3074. Min Act: -0.0000

Data Index: 314433 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3034. Min Act: -0.0000

Data Index: 78321 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1254251 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2766. Min Act: -0.0000

Data Index: 522567 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2945. Min Act: -0.0000

Data Index: 1111320 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.3628. Min Range: -0.3628

Max Act: 0.2849. Min Act: -0.0000

Data Index: 736799 (C4 (Web Text))

Max Activating Token Index: 277