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

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

Neuron 2689 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.4353. Min Act: -0.0000

Data Index: 1357445 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3860. Min Act: -0.0001

Data Index: 942016 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3797. Min Act: -0.0001

Data Index: 430662 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3646. Min Act: -0.0001

Data Index: 969756 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3471. Min Act: -0.0000

Data Index: 544653 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3343. Min Act: -0.0001

Data Index: 886764 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3441. Min Act: -0.0001

Data Index: 927562 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3243. Min Act: -0.0001

Data Index: 456111 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3348. Min Act: -0.0001

Data Index: 683237 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3275. Min Act: -0.0001

Data Index: 263481 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3278. Min Act: -0.0001

Data Index: 1359226 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3502. Min Act: -0.0001

Data Index: 104801 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3216. Min Act: -0.0001

Data Index: 1315772 (C4 (Web Text))

Max Activating Token Index: 975

Text #13

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3060. Min Act: -0.0001

Data Index: 239485 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3043. Min Act: -0.0001

Data Index: 403784 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3038. Min Act: -0.0001

Data Index: 1303955 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3095. Min Act: -0.0001

Data Index: 366038 (C4 (Web Text))

Max Activating Token Index: 899

Text #17

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3271. Min Act: -0.0001

Data Index: 1067783 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3207. Min Act: -0.0001

Data Index: 724901 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.4353. Min Range: -0.4353

Max Act: 0.3015. Min Act: -0.0001

Data Index: 1002375 (C4 (Web Text))

Max Activating Token Index: 22