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

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

Neuron 5267 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: 0.0736. Min Range: -0.0736

Max Act: 0.0736. Min Act: -0.0003

Data Index: 1282305 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0715. Min Act: -0.0002

Data Index: 728278 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0590. Min Act: -0.0002

Data Index: 669583 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0605. Min Act: -0.0002

Data Index: 358149 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0492. Min Act: -0.0002

Data Index: 653949 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0477. Min Act: -0.0002

Data Index: 791580 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0433. Min Act: -0.0002

Data Index: 715786 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0425. Min Act: -0.0003

Data Index: 1082274 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0414. Min Act: -0.0002

Data Index: 174490 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1120143 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0392. Min Act: -0.0002

Data Index: 24197 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0393. Min Act: -0.0003

Data Index: 269048 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0369. Min Act: -0.0002

Data Index: 704323 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0354. Min Act: -0.0002

Data Index: 426005 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0354. Min Act: -0.0002

Data Index: 623755 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0349. Min Act: -0.0003

Data Index: 55777 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1120388 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0341. Min Act: -0.0002

Data Index: 1125297 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0331. Min Act: -0.0003

Data Index: 300439 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0330. Min Act: -0.0002

Data Index: 450485 (C4 (Web Text))

Max Activating Token Index: 1023