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

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

Neuron 4900 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8834. Min Act: -0.0002

Data Index: 816766 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8531. Min Act: -0.0002

Data Index: 465788 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8222. Min Act: -0.0002

Data Index: 204172 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.8032. Min Act: -0.0002

Data Index: 1099371 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7822. Min Act: -0.0002

Data Index: 1223431 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7773. Min Act: -0.0002

Data Index: 944620 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7801. Min Act: -0.0002

Data Index: 506859 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7873. Min Act: -0.0002

Data Index: 157177 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7790. Min Act: -0.0002

Data Index: 1010207 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7588. Min Act: -0.0002

Data Index: 354873 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7677. Min Act: -0.0002

Data Index: 300517 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7528. Min Act: -0.0002

Data Index: 1197222 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7537. Min Act: -0.0002

Data Index: 980292 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7590. Min Act: -0.0002

Data Index: 1226933 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7546. Min Act: -0.0001

Data Index: 1270292 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7576. Min Act: -0.0002

Data Index: 1027002 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7284. Min Act: -0.0002

Data Index: 144208 (C4 (Web Text))

Max Activating Token Index: 856

Text #17

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7422. Min Act: -0.0002

Data Index: 610890 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7380. Min Act: -0.0002

Data Index: 6004 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.8834. Min Range: -0.8834

Max Act: 0.7506. Min Act: -0.0002

Data Index: 244556 (C4 (Web Text))

Max Activating Token Index: 983