Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3739 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.6844. Min Act: -0.0000

Data Index: 1246757 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.6423. Min Act: -0.0000

Data Index: 291695 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.6307. Min Act: -0.0000

Data Index: 555864 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.6191. Min Act: -0.0000

Data Index: 533984 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.6252. Min Act: -0.0001

Data Index: 433968 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.6217. Min Act: -0.0000

Data Index: 710826 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.5367. Min Act: -0.0000

Data Index: 658647 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.5277. Min Act: -0.0000

Data Index: 622938 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4612. Min Act: -0.0000

Data Index: 423004 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1288682 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4140. Min Act: 0.0000

Data Index: 491182 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4222. Min Act: -0.0000

Data Index: 254723 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4175. Min Act: 0.0000

Data Index: 1068640 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1296467 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4165. Min Act: -0.0000

Data Index: 73264 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4078. Min Act: -0.0000

Data Index: 61648 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1260774 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4258. Min Act: -0.0000

Data Index: 257869 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.4002. Min Act: -0.0001

Data Index: 1009175 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.6844. Min Range: -0.6844

Max Act: 0.3962. Min Act: -0.0000

Data Index: 864772 (C4 (Web Text))

Max Activating Token Index: 596