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

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

Neuron 653 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: 0.0439. Min Range: -0.0439

Max Act: 0.0439. Min Act: -0.0006

Data Index: 1423316 (Python Code)

Max Activating Token Index: 42

Text #1

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0419. Min Act: -0.0006

Data Index: 1173306 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0236. Min Act: -0.0006

Data Index: 673779 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0223. Min Act: -0.0006

Data Index: 1044588 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0215. Min Act: -0.0006

Data Index: 1483328 (Python Code)

Max Activating Token Index: 983

Text #5

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0199. Min Act: -0.0006

Data Index: 1214825 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0199. Min Act: -0.0006

Data Index: 87020 (C4 (Web Text))

Max Activating Token Index: 413

Text #7

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0178. Min Act: -0.0006

Data Index: 1623386 (Python Code)

Max Activating Token Index: 944

Text #8

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1414070 (Python Code)

Max Activating Token Index: 934

Text #9

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1189381 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1517504 (Python Code)

Max Activating Token Index: 423

Text #11

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0173. Min Act: -0.0006

Data Index: 118289 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1586329 (Python Code)

Max Activating Token Index: 678

Text #13

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0165. Min Act: -0.0006

Data Index: 1394924 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0161. Min Act: -0.0006

Data Index: 1476792 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0165. Min Act: -0.0006

Data Index: 1525292 (Python Code)

Max Activating Token Index: 676

Text #16

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0164. Min Act: -0.0006

Data Index: 675468 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0163. Min Act: -0.0006

Data Index: 1147064 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0157. Min Act: -0.0005

Data Index: 1637348 (Python Code)

Max Activating Token Index: 300

Text #19

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1111099 (C4 (Web Text))

Max Activating Token Index: 1014