Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 380 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0171. Min Act: -0.0006

Data Index: 446543 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0145. Min Act: -0.0006

Data Index: 449398 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0137. Min Act: -0.0006

Data Index: 114833 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0152. Min Act: -0.0006

Data Index: 627228 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0144. Min Act: -0.0006

Data Index: 175585 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0137. Min Act: -0.0006

Data Index: 1345038 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0143. Min Act: -0.0006

Data Index: 534816 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0139. Min Act: -0.0006

Data Index: 770468 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0136. Min Act: -0.0006

Data Index: 469612 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0141. Min Act: -0.0005

Data Index: 17504 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0142. Min Act: -0.0006

Data Index: 304941 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0132. Min Act: -0.0006

Data Index: 306888 (C4 (Web Text))

Max Activating Token Index: 904

Text #12

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0129. Min Act: -0.0006

Data Index: 890455 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0140. Min Act: -0.0005

Data Index: 371882 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0130. Min Act: -0.0006

Data Index: 774535 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0130. Min Act: -0.0006

Data Index: 552086 (C4 (Web Text))

Max Activating Token Index: 151

Text #16

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0118. Min Act: -0.0006

Data Index: 398424 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0129. Min Act: -0.0006

Data Index: 1245232 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0127. Min Act: -0.0006

Data Index: 131924 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 0.0171. Min Range: -0.0171

Max Act: 0.0126. Min Act: -0.0005

Data Index: 1082533 (C4 (Web Text))

Max Activating Token Index: 723