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

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

Neuron 1306 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2490. Min Range: -2.2490

Max Act: 2.2490. Min Act: -0.0000

Data Index: 770244 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 2.2490. Min Range: -2.2490

Max Act: 2.0754. Min Act: -0.0000

Data Index: 1045458 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.9105. Min Act: -0.0000

Data Index: 947115 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.9217. Min Act: -0.0000

Data Index: 1186798 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.7688. Min Act: -0.0000

Data Index: 1380744 (Python Code)

Max Activating Token Index: 461

Text #5

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.8277. Min Act: -0.0000

Data Index: 841833 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.7782. Min Act: -0.0000

Data Index: 200193 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.5784. Min Act: -0.0000

Data Index: 1608681 (Python Code)

Max Activating Token Index: 815

Text #8

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.6027. Min Act: -0.0000

Data Index: 957397 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.5073. Min Act: -0.0000

Data Index: 1431009 (Python Code)

Max Activating Token Index: 424

Text #10

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.4561. Min Act: -0.0000

Data Index: 1190591 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.3476. Min Act: -0.0000

Data Index: 1592557 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.4477. Min Act: -0.0000

Data Index: 888974 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.2475. Min Act: -0.0000

Data Index: 1332146 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.4607. Min Act: -0.0000

Data Index: 80514 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.3990. Min Act: -0.0000

Data Index: 5275 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.3959. Min Act: -0.0000

Data Index: 1105179 (C4 (Web Text))

Max Activating Token Index: 926

Text #17

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.4026. Min Act: -0.0000

Data Index: 1653799 (Python Code)

Max Activating Token Index: 534

Text #18

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.3441. Min Act: -0.0000

Data Index: 854002 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 2.2490. Min Range: -2.2490

Max Act: 1.2819. Min Act: -0.0000

Data Index: 870572 (C4 (Web Text))

Max Activating Token Index: 299