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

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

Neuron 2625 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: 6.2335. Min Range: -6.2335

Max Act: 6.2335. Min Act: -0.0000

Data Index: 1347944 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 6.2335. Min Range: -6.2335

Max Act: 5.6408. Min Act: -0.0000

Data Index: 484414 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 6.2335. Min Range: -6.2335

Max Act: 5.7819. Min Act: -0.0000

Data Index: 568178 (C4 (Web Text))

Max Activating Token Index: 191

Text #3

Max Range: 6.2335. Min Range: -6.2335

Max Act: 5.3140. Min Act: -0.0000

Data Index: 621703 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 6.2335. Min Range: -6.2335

Max Act: 5.8391. Min Act: -0.0000

Data Index: 1294085 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 6.2335. Min Range: -6.2335

Max Act: 5.8091. Min Act: -0.0000

Data Index: 1174544 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 6.2335. Min Range: -6.2335

Max Act: 5.2831. Min Act: -0.0000

Data Index: 1009559 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 6.2335. Min Range: -6.2335

Max Act: 5.1660. Min Act: -0.0000

Data Index: 728653 (C4 (Web Text))

Max Activating Token Index: 863

Text #8

Max Range: 6.2335. Min Range: -6.2335

Max Act: 5.5185. Min Act: -0.0000

Data Index: 262918 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 6.2335. Min Range: -6.2335

Max Act: 4.7981. Min Act: -0.0000

Data Index: 749941 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 6.2335. Min Range: -6.2335

Max Act: 4.9100. Min Act: -0.0000

Data Index: 1062629 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 6.2335. Min Range: -6.2335

Max Act: 4.9032. Min Act: -0.0000

Data Index: 505549 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 6.2335. Min Range: -6.2335

Max Act: 4.7562. Min Act: -0.0000

Data Index: 33521 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 6.2335. Min Range: -6.2335

Max Act: 5.1014. Min Act: -0.0000

Data Index: 676266 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 6.2335. Min Range: -6.2335

Max Act: 5.4032. Min Act: -0.0000

Data Index: 433292 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 6.2335. Min Range: -6.2335

Max Act: 4.6836. Min Act: -0.0000

Data Index: 1027090 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 6.2335. Min Range: -6.2335

Max Act: 5.4060. Min Act: -0.0000

Data Index: 314056 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 6.2335. Min Range: -6.2335

Max Act: 4.6618. Min Act: -0.0000

Data Index: 946511 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 6.2335. Min Range: -6.2335

Max Act: 4.7921. Min Act: -0.0000

Data Index: 395172 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 6.2335. Min Range: -6.2335

Max Act: 4.4589. Min Act: -0.0000

Data Index: 363207 (C4 (Web Text))

Max Activating Token Index: 402