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

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

Neuron 1878 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: 1.9804. Min Range: -1.9804

Max Act: 1.9804. Min Act: -0.0002

Data Index: 824175 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.8695. Min Act: -0.0002

Data Index: 1354425 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.8774. Min Act: -0.0002

Data Index: 1354964 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.8275. Min Act: -0.0002

Data Index: 1009536 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.7824. Min Act: -0.0002

Data Index: 247253 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.7892. Min Act: -0.0002

Data Index: 1006039 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.8079. Min Act: -0.0002

Data Index: 683735 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.7672. Min Act: -0.0002

Data Index: 719388 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.8032. Min Act: -0.0002

Data Index: 305779 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.7980. Min Act: -0.0002

Data Index: 447403 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.7993. Min Act: -0.0002

Data Index: 171065 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.7678. Min Act: -0.0002

Data Index: 841419 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.7791. Min Act: -0.0002

Data Index: 1109608 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.7283. Min Act: -0.0002

Data Index: 589362 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.7222. Min Act: -0.0002

Data Index: 968737 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.7306. Min Act: -0.0002

Data Index: 1214223 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.7239. Min Act: -0.0002

Data Index: 1300357 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.7387. Min Act: -0.0002

Data Index: 1281777 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.7523. Min Act: -0.0002

Data Index: 997221 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 1.9804. Min Range: -1.9804

Max Act: 1.7311. Min Act: -0.0002

Data Index: 742911 (C4 (Web Text))

Max Activating Token Index: 184