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

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

Neuron 328 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0176. Min Act: -0.0003

Data Index: 482547 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0168. Min Act: -0.0003

Data Index: 643135 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0134. Min Act: -0.0003

Data Index: 604010 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0127. Min Act: -0.0003

Data Index: 941297 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0114. Min Act: -0.0003

Data Index: 736090 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0117. Min Act: -0.0003

Data Index: 1171838 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0118. Min Act: -0.0004

Data Index: 1310237 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0117. Min Act: -0.0003

Data Index: 942458 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0110. Min Act: -0.0003

Data Index: 460069 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0111. Min Act: -0.0003

Data Index: 1137367 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0106. Min Act: -0.0003

Data Index: 200813 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0111. Min Act: -0.0003

Data Index: 1361219 (Python Code)

Max Activating Token Index: 256

Text #12

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0096. Min Act: -0.0003

Data Index: 873234 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0092. Min Act: -0.0003

Data Index: 155187 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0096. Min Act: -0.0003

Data Index: 159228 (C4 (Web Text))

Max Activating Token Index: 452

Text #15

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0110. Min Act: -0.0003

Data Index: 141574 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0101. Min Act: -0.0003

Data Index: 242860 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0100. Min Act: -0.0003

Data Index: 53499 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0107. Min Act: -0.0003

Data Index: 1069691 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0093. Min Act: -0.0003

Data Index: 145956 (C4 (Web Text))

Max Activating Token Index: 297