Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1434 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.3546. Min Act: -0.0001

Data Index: 756561 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.3210. Min Act: -0.0001

Data Index: 1296711 (C4 (Web Text))

Max Activating Token Index: 190

Text #2

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.3408. Min Act: -0.0001

Data Index: 850604 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.3362. Min Act: -0.0001

Data Index: 477334 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.3042. Min Act: -0.0001

Data Index: 295766 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.3148. Min Act: -0.0001

Data Index: 1293603 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.3239. Min Act: -0.0001

Data Index: 1356268 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.2966. Min Act: -0.0001

Data Index: 262807 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.2981. Min Act: -0.0001

Data Index: 57999 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.2837. Min Act: -0.0001

Data Index: 536546 (C4 (Web Text))

Max Activating Token Index: 1005

Text #10

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.2899. Min Act: -0.0001

Data Index: 181133 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.2881. Min Act: -0.0000

Data Index: 793306 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.2878. Min Act: -0.0001

Data Index: 722569 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.2867. Min Act: -0.0001

Data Index: 1245855 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.2868. Min Act: -0.0000

Data Index: 19408 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.2651. Min Act: -0.0001

Data Index: 232906 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.2926. Min Act: -0.0001

Data Index: 304464 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.2894. Min Act: -0.0001

Data Index: 887485 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.2872. Min Act: -0.0001

Data Index: 817670 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.3546. Min Range: -0.3546

Max Act: 0.2818. Min Act: -0.0001

Data Index: 907251 (C4 (Web Text))

Max Activating Token Index: 940