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

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

Neuron 4117 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: 3.4884. Min Range: -3.4884

Max Act: 3.4884. Min Act: -0.0000

Data Index: 887352 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 3.4884. Min Range: -3.4884

Max Act: 3.0040. Min Act: -0.0000

Data Index: 1273610 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 3.4884. Min Range: -3.4884

Max Act: 3.1775. Min Act: -0.0000

Data Index: 603401 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.9873. Min Act: -0.0000

Data Index: 434662 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.9027. Min Act: -0.0000

Data Index: 1095064 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.6323. Min Act: -0.0000

Data Index: 613370 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.7492. Min Act: -0.0000

Data Index: 1269169 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.5895. Min Act: -0.0000

Data Index: 462338 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.5793. Min Act: -0.0000

Data Index: 780872 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.7239. Min Act: -0.0000

Data Index: 843581 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.5441. Min Act: -0.0000

Data Index: 219070 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.6264. Min Act: -0.0000

Data Index: 285534 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.6021. Min Act: -0.0000

Data Index: 1247616 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.7700. Min Act: -0.0000

Data Index: 1315862 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.7262. Min Act: -0.0000

Data Index: 121185 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.5749. Min Act: -0.0000

Data Index: 124097 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.4621. Min Act: -0.0000

Data Index: 1178776 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.5856. Min Act: -0.0000

Data Index: 331826 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.6988. Min Act: -0.0000

Data Index: 653483 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 3.4884. Min Range: -3.4884

Max Act: 2.4155. Min Act: -0.0000

Data Index: 361970 (C4 (Web Text))

Max Activating Token Index: 628