Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1295 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3865. Min Act: -0.0001

Data Index: 818437 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2559. Min Act: -0.0001

Data Index: 670333 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3176. Min Act: -0.0001

Data Index: 742528 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2948. Min Act: -0.0001

Data Index: 131617 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2812. Min Act: -0.0001

Data Index: 91353 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2641. Min Act: -0.0001

Data Index: 608027 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.3330. Min Act: -0.0001

Data Index: 1086487 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2501. Min Act: -0.0001

Data Index: 1042411 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2768. Min Act: -0.0001

Data Index: 266175 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2275. Min Act: -0.0001

Data Index: 1138352 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2313. Min Act: -0.0001

Data Index: 155264 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2087. Min Act: -0.0001

Data Index: 418888 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1915. Min Act: -0.0001

Data Index: 336292 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.2034. Min Act: -0.0001

Data Index: 393860 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1822. Min Act: -0.0001

Data Index: 635304 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1719. Min Act: -0.0001

Data Index: 349530 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1868. Min Act: -0.0001

Data Index: 555810 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1802. Min Act: -0.0001

Data Index: 1017249 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1648. Min Act: -0.0001

Data Index: 468118 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.3865. Min Range: -0.3865

Max Act: 0.1748. Min Act: -0.0001

Data Index: 64214 (C4 (Web Text))

Max Activating Token Index: 344