Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2469 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.9878. Min Act: -0.0000

Data Index: 1441105 (Python Code)

Max Activating Token Index: 96

Text #1

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.9900. Min Act: -0.0000

Data Index: 777502 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.9712. Min Act: -0.0000

Data Index: 333401 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 1.0555. Min Range: -1.0555

Max Act: 1.0555. Min Act: -0.0000

Data Index: 238383 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.8741. Min Act: -0.0000

Data Index: 221387 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.8773. Min Act: -0.0000

Data Index: 1485936 (Python Code)

Max Activating Token Index: 664

Text #6

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.8968. Min Act: -0.0000

Data Index: 1406484 (Python Code)

Max Activating Token Index: 638

Text #7

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1638424 (Python Code)

Max Activating Token Index: 163

Text #8

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.7700. Min Act: -0.0000

Data Index: 285789 (C4 (Web Text))

Max Activating Token Index: 512

Text #9

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.7340. Min Act: -0.0000

Data Index: 1443102 (Python Code)

Max Activating Token Index: 235

Text #10

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.7810. Min Act: -0.0000

Data Index: 867737 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.7308. Min Act: -0.0000

Data Index: 745472 (C4 (Web Text))

Max Activating Token Index: 515

Text #12

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1573422 (Python Code)

Max Activating Token Index: 425

Text #13

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1031308 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.7224. Min Act: -0.0000

Data Index: 281499 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.7128. Min Act: -0.0000

Data Index: 1470150 (Python Code)

Max Activating Token Index: 704

Text #16

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1512105 (Python Code)

Max Activating Token Index: 65

Text #17

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.7311. Min Act: -0.0000

Data Index: 557318 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1258835 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 1.0555. Min Range: -1.0555

Max Act: 0.6607. Min Act: -0.0000

Data Index: 696955 (C4 (Web Text))

Max Activating Token Index: 960