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

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

Neuron 393 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3032. Min Range: -2.3032

Max Act: 2.2246. Min Act: -0.0000

Data Index: 3921 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 2.3032. Min Range: -2.3032

Max Act: 2.3032. Min Act: -0.0000

Data Index: 407364 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.9456. Min Act: -0.0000

Data Index: 423100 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 2.3032. Min Range: -2.3032

Max Act: 2.0136. Min Act: -0.0000

Data Index: 167296 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.8810. Min Act: -0.0000

Data Index: 894237 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.9544. Min Act: -0.0000

Data Index: 522600 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.7764. Min Act: -0.0000

Data Index: 1572576 (Python Code)

Max Activating Token Index: 614

Text #7

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.7942. Min Act: -0.0000

Data Index: 260446 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.8467. Min Act: -0.0000

Data Index: 1565305 (Python Code)

Max Activating Token Index: 454

Text #9

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.7767. Min Act: -0.0000

Data Index: 1484928 (Python Code)

Max Activating Token Index: 1015

Text #10

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.7492. Min Act: -0.0000

Data Index: 18348 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.7425. Min Act: -0.0000

Data Index: 959261 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.6516. Min Act: -0.0000

Data Index: 1031288 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.7199. Min Act: -0.0000

Data Index: 978645 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.7206. Min Act: -0.0000

Data Index: 1372629 (Python Code)

Max Activating Token Index: 321

Text #15

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.6553. Min Act: -0.0000

Data Index: 1483132 (Python Code)

Max Activating Token Index: 563

Text #16

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.7043. Min Act: -0.0000

Data Index: 385418 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.5677. Min Act: -0.0000

Data Index: 962177 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.7024. Min Act: -0.0000

Data Index: 1298644 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 2.3032. Min Range: -2.3032

Max Act: 1.6279. Min Act: -0.0000

Data Index: 1420923 (Python Code)

Max Activating Token Index: 520