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

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

Neuron 921 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: 1.4069. Min Range: -1.4069

Max Act: 1.4069. Min Act: 0.0000

Data Index: 315144 (C4 (Web Text))

Max Activating Token Index: 132

Text #1

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.1722. Min Act: -0.0000

Data Index: 630630 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.1874. Min Act: -0.0000

Data Index: 993236 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0486. Min Act: 0.0000

Data Index: 762225 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0676. Min Act: -0.0000

Data Index: 154273 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0334. Min Act: -0.0000

Data Index: 367187 (C4 (Web Text))

Max Activating Token Index: 885

Text #6

Max Range: 1.4069. Min Range: -1.4069

Max Act: 1.0449. Min Act: -0.0000

Data Index: 1357684 (C4 (Web Text))

Max Activating Token Index: 391

Text #7

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.8832. Min Act: -0.0000

Data Index: 271285 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.9317. Min Act: -0.0000

Data Index: 1102230 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.9506. Min Act: -0.0000

Data Index: 1116669 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.8911. Min Act: -0.0000

Data Index: 1245751 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.8491. Min Act: -0.0000

Data Index: 266408 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.8615. Min Act: -0.0000

Data Index: 1024140 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.8818. Min Act: -0.0000

Data Index: 305850 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.8307. Min Act: -0.0000

Data Index: 561673 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.8008. Min Act: -0.0000

Data Index: 589323 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.8189. Min Act: -0.0000

Data Index: 889562 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.7860. Min Act: -0.0000

Data Index: 728366 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.7812. Min Act: -0.0000

Data Index: 421622 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 1.4069. Min Range: -1.4069

Max Act: 0.7256. Min Act: -0.0000

Data Index: 1294182 (C4 (Web Text))

Max Activating Token Index: 164