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

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

Neuron 1621 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.8348. Min Act: -0.0000

Data Index: 588013 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.8044. Min Act: -0.0000

Data Index: 66572 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1245147 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.7138. Min Act: -0.0000

Data Index: 273701 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6833. Min Act: -0.0000

Data Index: 457317 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.7227. Min Act: -0.0000

Data Index: 628251 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.7223. Min Act: -0.0000

Data Index: 217264 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6975. Min Act: -0.0000

Data Index: 1049764 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1219678 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.7142. Min Act: -0.0000

Data Index: 334727 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6462. Min Act: -0.0000

Data Index: 263053 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6896. Min Act: -0.0000

Data Index: 257126 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6811. Min Act: -0.0000

Data Index: 153249 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6253. Min Act: -0.0000

Data Index: 623305 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1000396 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6229. Min Act: -0.0000

Data Index: 271263 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6281. Min Act: -0.0000

Data Index: 676740 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6213. Min Act: -0.0000

Data Index: 713924 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6397. Min Act: -0.0000

Data Index: 1235972 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6120. Min Act: -0.0000

Data Index: 821614 (C4 (Web Text))

Max Activating Token Index: 85