Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1498 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0457. Min Act: -0.0004

Data Index: 40676 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0446. Min Act: -0.0004

Data Index: 420140 (C4 (Web Text))

Max Activating Token Index: 187

Text #2

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0430. Min Act: -0.0004

Data Index: 650198 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0414. Min Act: -0.0004

Data Index: 874934 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0414. Min Act: -0.0004

Data Index: 1008626 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0414. Min Act: -0.0004

Data Index: 100077 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0420. Min Act: -0.0004

Data Index: 1358224 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0409. Min Act: -0.0004

Data Index: 603158 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0429. Min Act: -0.0004

Data Index: 613969 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0416. Min Act: -0.0004

Data Index: 787551 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0418. Min Act: -0.0004

Data Index: 1087362 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0416. Min Act: -0.0004

Data Index: 1466486 (Python Code)

Max Activating Token Index: 165

Text #12

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0414. Min Act: -0.0004

Data Index: 463162 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0383. Min Act: -0.0004

Data Index: 1218328 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0428. Min Act: -0.0004

Data Index: 406583 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0409. Min Act: -0.0004

Data Index: 999219 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0401. Min Act: -0.0004

Data Index: 1211977 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0408. Min Act: -0.0004

Data Index: 838127 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0408. Min Act: -0.0004

Data Index: 100931 (C4 (Web Text))

Max Activating Token Index: 3

Text #19

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0408. Min Act: -0.0004

Data Index: 1273046 (C4 (Web Text))

Max Activating Token Index: 3