Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 391 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2961. Min Act: -0.0001

Data Index: 532960 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2573. Min Act: -0.0001

Data Index: 713215 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2475. Min Act: -0.0001

Data Index: 636221 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2360. Min Act: -0.0001

Data Index: 473719 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2278. Min Act: -0.0001

Data Index: 643464 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2232. Min Act: -0.0001

Data Index: 355657 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2115. Min Act: -0.0001

Data Index: 359104 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2163. Min Act: -0.0001

Data Index: 1357817 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2143. Min Act: -0.0001

Data Index: 1147313 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2084. Min Act: -0.0001

Data Index: 1165936 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2222. Min Act: -0.0001

Data Index: 726847 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2126. Min Act: -0.0001

Data Index: 569350 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2118. Min Act: -0.0001

Data Index: 433230 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2090. Min Act: -0.0001

Data Index: 1210328 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2072. Min Act: -0.0000

Data Index: 300155 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2091. Min Act: -0.0000

Data Index: 535114 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1152003 (C4 (Web Text))

Max Activating Token Index: 204

Text #17

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.1998. Min Act: -0.0001

Data Index: 21116 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.2120. Min Act: -0.0001

Data Index: 174019 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.2961. Min Range: -0.2961

Max Act: 0.1942. Min Act: -0.0001

Data Index: 317315 (C4 (Web Text))

Max Activating Token Index: 72