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

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

Neuron 3515 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2943. Min Act: -0.0000

Data Index: 822515 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2667. Min Act: -0.0000

Data Index: 480393 (C4 (Web Text))

Max Activating Token Index: 865

Text #2

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2742. Min Act: -0.0000

Data Index: 962057 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2657. Min Act: -0.0000

Data Index: 765936 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2500. Min Act: -0.0000

Data Index: 299836 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2201. Min Act: -0.0000

Data Index: 26033 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2450. Min Act: -0.0000

Data Index: 77276 (C4 (Web Text))

Max Activating Token Index: 865

Text #7

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2468. Min Act: -0.0000

Data Index: 672904 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2435. Min Act: -0.0000

Data Index: 618883 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2414. Min Act: -0.0000

Data Index: 1294432 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2396. Min Act: -0.0000

Data Index: 1109359 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2387. Min Act: -0.0000

Data Index: 423190 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2378. Min Act: -0.0000

Data Index: 383729 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2355. Min Act: -0.0000

Data Index: 740202 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1152626 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2331. Min Act: -0.0000

Data Index: 291207 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2376. Min Act: -0.0000

Data Index: 955780 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2249. Min Act: -0.0000

Data Index: 337009 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2323. Min Act: -0.0000

Data Index: 248663 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.2943. Min Range: -0.2943

Max Act: 0.2252. Min Act: -0.0000

Data Index: 816889 (C4 (Web Text))

Max Activating Token Index: 562