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

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

Neuron 4437 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.6044. Min Act: -0.0000

Data Index: 557763 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4840. Min Act: -0.0000

Data Index: 334548 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1260440 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4425. Min Act: -0.0000

Data Index: 65159 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4592. Min Act: -0.0000

Data Index: 828125 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4376. Min Act: -0.0000

Data Index: 348174 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4316. Min Act: -0.0000

Data Index: 740334 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4073. Min Act: -0.0000

Data Index: 470848 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3962. Min Act: -0.0000

Data Index: 361007 (C4 (Web Text))

Max Activating Token Index: 254

Text #9

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4190. Min Act: -0.0000

Data Index: 991169 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4070. Min Act: -0.0000

Data Index: 167142 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4312. Min Act: -0.0000

Data Index: 350047 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4126. Min Act: -0.0000

Data Index: 322944 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4116. Min Act: -0.0000

Data Index: 785850 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4096. Min Act: -0.0000

Data Index: 686488 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3955. Min Act: -0.0000

Data Index: 640880 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4054. Min Act: -0.0000

Data Index: 536645 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4009. Min Act: -0.0000

Data Index: 205731 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.4129. Min Act: -0.0000

Data Index: 38528 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 0.6044. Min Range: -0.6044

Max Act: 0.3987. Min Act: -0.0000

Data Index: 1353567 (C4 (Web Text))

Max Activating Token Index: 571