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

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

Neuron 2554 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: 0.8089. Min Range: -0.8089

Max Act: 0.7965. Min Act: -0.0002

Data Index: 1050331 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7948. Min Act: -0.0002

Data Index: 743447 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.8089. Min Act: -0.0002

Data Index: 50662 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7805. Min Act: -0.0002

Data Index: 1339888 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7953. Min Act: -0.0002

Data Index: 1115065 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7767. Min Act: -0.0002

Data Index: 484263 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7611. Min Act: -0.0002

Data Index: 16332 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7757. Min Act: -0.0002

Data Index: 506677 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7693. Min Act: -0.0002

Data Index: 663078 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7614. Min Act: -0.0002

Data Index: 763516 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7525. Min Act: -0.0002

Data Index: 339719 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7302. Min Act: -0.0002

Data Index: 167470 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7403. Min Act: -0.0002

Data Index: 159418 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7462. Min Act: -0.0002

Data Index: 882468 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7247. Min Act: -0.0002

Data Index: 1061813 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7267. Min Act: -0.0002

Data Index: 201187 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7351. Min Act: -0.0002

Data Index: 1331073 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7232. Min Act: -0.0002

Data Index: 713877 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7258. Min Act: -0.0002

Data Index: 703366 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 0.8089. Min Range: -0.8089

Max Act: 0.7375. Min Act: -0.0002

Data Index: 1146994 (C4 (Web Text))

Max Activating Token Index: 32