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

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

Neuron 2536 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0671. Min Act: -0.0003

Data Index: 251696 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0516. Min Act: -0.0002

Data Index: 141632 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0505. Min Act: -0.0003

Data Index: 825101 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0467. Min Act: -0.0003

Data Index: 997600 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0468. Min Act: -0.0003

Data Index: 659155 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0451. Min Act: -0.0003

Data Index: 225633 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0446. Min Act: -0.0003

Data Index: 334557 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1161975 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1099612 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0457. Min Act: -0.0002

Data Index: 65923 (C4 (Web Text))

Max Activating Token Index: 934

Text #10

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0448. Min Act: -0.0002

Data Index: 390166 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0445. Min Act: -0.0003

Data Index: 310587 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0430. Min Act: -0.0003

Data Index: 1184018 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0448. Min Act: -0.0003

Data Index: 1238153 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0437. Min Act: -0.0003

Data Index: 440345 (C4 (Web Text))

Max Activating Token Index: 497

Text #15

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0435. Min Act: -0.0003

Data Index: 175918 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0440. Min Act: -0.0003

Data Index: 390322 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0431. Min Act: -0.0003

Data Index: 312787 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0422. Min Act: -0.0003

Data Index: 742452 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.0671. Min Range: -0.0671

Max Act: 0.0410. Min Act: -0.0003

Data Index: 6737 (C4 (Web Text))

Max Activating Token Index: 709