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

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

Neuron 834 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3960. Min Act: -0.0000

Data Index: 187745 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3851. Min Act: -0.0000

Data Index: 955570 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1143515 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3490. Min Act: -0.0000

Data Index: 569153 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1354633 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3227. Min Act: -0.0000

Data Index: 1317352 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1049883 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2962. Min Act: -0.0000

Data Index: 371619 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2851. Min Act: -0.0000

Data Index: 199606 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2917. Min Act: -0.0000

Data Index: 1186670 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2909. Min Act: -0.0000

Data Index: 1327893 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.3160. Min Act: -0.0000

Data Index: 822780 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2819. Min Act: -0.0000

Data Index: 195869 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2974. Min Act: -0.0000

Data Index: 198751 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2740. Min Act: -0.0000

Data Index: 673257 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2450. Min Act: -0.0000

Data Index: 822799 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2688. Min Act: -0.0000

Data Index: 1331675 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2479. Min Act: -0.0000

Data Index: 318173 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2537. Min Act: 0.0000

Data Index: 70208 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.3960. Min Range: -0.3960

Max Act: 0.2499. Min Act: -0.0000

Data Index: 1131779 (C4 (Web Text))

Max Activating Token Index: 385