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

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

Neuron 1229 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: 1.7577. Min Range: -1.7577

Max Act: 1.5759. Min Act: -0.0000

Data Index: 190745 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.7577. Min Act: -0.0000

Data Index: 424680 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.7453. Min Act: -0.0000

Data Index: 779384 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.4564. Min Act: -0.0000

Data Index: 872778 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.5178. Min Act: -0.0000

Data Index: 132264 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.3949. Min Act: -0.0000

Data Index: 835421 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.3392. Min Act: -0.0000

Data Index: 433446 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.3958. Min Act: -0.0000

Data Index: 384529 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.3179. Min Act: -0.0000

Data Index: 937518 (C4 (Web Text))

Max Activating Token Index: 466

Text #9

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.3056. Min Act: -0.0000

Data Index: 1283813 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.1757. Min Act: -0.0000

Data Index: 349306 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.1629. Min Act: -0.0000

Data Index: 1177307 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.2066. Min Act: -0.0000

Data Index: 12350 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1202421 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.1770. Min Act: -0.0000

Data Index: 119588 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.1641. Min Act: -0.0000

Data Index: 749976 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.0662. Min Act: -0.0000

Data Index: 699333 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.0511. Min Act: -0.0000

Data Index: 653202 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.0430. Min Act: -0.0000

Data Index: 1186646 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 1.7577. Min Range: -1.7577

Max Act: 1.1089. Min Act: -0.0000

Data Index: 113410 (C4 (Web Text))

Max Activating Token Index: 615