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

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

Neuron 1064 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9068. Min Range: -3.9068

Max Act: 3.9068. Min Act: -0.0000

Data Index: 1487947 (Python Code)

Max Activating Token Index: 522

Text #1

Max Range: 3.9068. Min Range: -3.9068

Max Act: 3.3174. Min Act: -0.0000

Data Index: 1366402 (Python Code)

Max Activating Token Index: 210

Text #2

Max Range: 3.9068. Min Range: -3.9068

Max Act: 3.5587. Min Act: -0.0000

Data Index: 576201 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 3.9068. Min Range: -3.9068

Max Act: 3.7192. Min Act: -0.0000

Data Index: 523775 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 3.9068. Min Range: -3.9068

Max Act: 3.3684. Min Act: -0.0000

Data Index: 805356 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 3.9068. Min Range: -3.9068

Max Act: 3.0869. Min Act: -0.0000

Data Index: 311562 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 3.9068. Min Range: -3.9068

Max Act: 3.2060. Min Act: -0.0000

Data Index: 918686 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 3.9068. Min Range: -3.9068

Max Act: 2.8520. Min Act: -0.0000

Data Index: 1261407 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 3.9068. Min Range: -3.9068

Max Act: 2.8323. Min Act: -0.0000

Data Index: 85332 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 3.9068. Min Range: -3.9068

Max Act: 2.8036. Min Act: -0.0000

Data Index: 664278 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 3.9068. Min Range: -3.9068

Max Act: 3.0176. Min Act: -0.0000

Data Index: 51960 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 3.9068. Min Range: -3.9068

Max Act: 2.7500. Min Act: -0.0000

Data Index: 176996 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 3.9068. Min Range: -3.9068

Max Act: 2.7579. Min Act: -0.0000

Data Index: 1244966 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 3.9068. Min Range: -3.9068

Max Act: 2.6875. Min Act: -0.0000

Data Index: 324697 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 3.9068. Min Range: -3.9068

Max Act: 2.6644. Min Act: -0.0000

Data Index: 387244 (C4 (Web Text))

Max Activating Token Index: 19

Text #15

Max Range: 3.9068. Min Range: -3.9068

Max Act: 2.5166. Min Act: -0.0000

Data Index: 903037 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 3.9068. Min Range: -3.9068

Max Act: 2.6344. Min Act: -0.0000

Data Index: 118215 (C4 (Web Text))

Max Activating Token Index: 652

Text #17

Max Range: 3.9068. Min Range: -3.9068

Max Act: 2.2557. Min Act: -0.0000

Data Index: 783743 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 3.9068. Min Range: -3.9068

Max Act: 2.7707. Min Act: -0.0000

Data Index: 608090 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 3.9068. Min Range: -3.9068

Max Act: 2.6385. Min Act: -0.0000

Data Index: 1146087 (C4 (Web Text))

Max Activating Token Index: 446