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

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

Neuron 4945 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8170. Min Range: -3.8170

Max Act: 3.8170. Min Act: -0.0001

Data Index: 582297 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 3.8170. Min Range: -3.8170

Max Act: 3.7976. Min Act: -0.0001

Data Index: 38874 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 3.8170. Min Range: -3.8170

Max Act: 3.5519. Min Act: -0.0001

Data Index: 141351 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 3.8170. Min Range: -3.8170

Max Act: 3.4904. Min Act: -0.0001

Data Index: 522612 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 3.8170. Min Range: -3.8170

Max Act: 3.1091. Min Act: -0.0001

Data Index: 187682 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 3.8170. Min Range: -3.8170

Max Act: 3.0581. Min Act: -0.0001

Data Index: 1075129 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 3.8170. Min Range: -3.8170

Max Act: 3.6362. Min Act: -0.0001

Data Index: 569689 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 3.8170. Min Range: -3.8170

Max Act: 3.2846. Min Act: -0.0001

Data Index: 244523 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 3.8170. Min Range: -3.8170

Max Act: 3.0844. Min Act: -0.0001

Data Index: 772345 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 3.8170. Min Range: -3.8170

Max Act: 3.0910. Min Act: -0.0001

Data Index: 29965 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 3.8170. Min Range: -3.8170

Max Act: 3.2154. Min Act: -0.0001

Data Index: 149372 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 3.8170. Min Range: -3.8170

Max Act: 3.0608. Min Act: -0.0001

Data Index: 1219029 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 3.8170. Min Range: -3.8170

Max Act: 2.6579. Min Act: -0.0001

Data Index: 157027 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 3.8170. Min Range: -3.8170

Max Act: 2.8896. Min Act: -0.0001

Data Index: 27687 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 3.8170. Min Range: -3.8170

Max Act: 2.8658. Min Act: -0.0001

Data Index: 400272 (C4 (Web Text))

Max Activating Token Index: 321

Text #15

Max Range: 3.8170. Min Range: -3.8170

Max Act: 3.0098. Min Act: -0.0001

Data Index: 1241926 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 3.8170. Min Range: -3.8170

Max Act: 3.0231. Min Act: -0.0001

Data Index: 723493 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 3.8170. Min Range: -3.8170

Max Act: 3.1298. Min Act: -0.0001

Data Index: 175174 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 3.8170. Min Range: -3.8170

Max Act: 2.9897. Min Act: -0.0001

Data Index: 12092 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 3.8170. Min Range: -3.8170

Max Act: 2.9514. Min Act: -0.0001

Data Index: 313185 (C4 (Web Text))

Max Activating Token Index: 486