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

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

Neuron 3828 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: 1.4333. Min Range: -1.4333

Max Act: 1.4204. Min Act: -0.0000

Data Index: 1138669 (C4 (Web Text))

Max Activating Token Index: 535

Text #1

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.3718. Min Act: -0.0000

Data Index: 197919 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.4333. Min Act: -0.0000

Data Index: 869617 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.3501. Min Act: -0.0000

Data Index: 1224723 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.2877. Min Act: -0.0000

Data Index: 1075788 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.2429. Min Act: -0.0000

Data Index: 708638 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.1969. Min Act: -0.0000

Data Index: 1190801 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.1928. Min Act: -0.0000

Data Index: 624106 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.1991. Min Act: -0.0000

Data Index: 941752 (C4 (Web Text))

Max Activating Token Index: 785

Text #9

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.1820. Min Act: -0.0000

Data Index: 425877 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.1638. Min Act: -0.0000

Data Index: 802883 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.0881. Min Act: -0.0000

Data Index: 309708 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.1057. Min Act: -0.0000

Data Index: 970849 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.1053. Min Act: -0.0000

Data Index: 360594 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.0346. Min Act: -0.0000

Data Index: 666114 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.0643. Min Act: -0.0000

Data Index: 253981 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.0770. Min Act: -0.0000

Data Index: 986103 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.0602. Min Act: -0.0000

Data Index: 1331376 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.0539. Min Act: -0.0000

Data Index: 8364 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.0473. Min Act: -0.0000

Data Index: 487900 (C4 (Web Text))

Max Activating Token Index: 732