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

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

Neuron 3052 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.6222. Min Act: -0.0000

Data Index: 159 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.5708. Min Act: -0.0000

Data Index: 78850 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.4715. Min Act: -0.0000

Data Index: 27180 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.6634. Min Act: -0.0000

Data Index: 181651 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.4078. Min Act: -0.0001

Data Index: 76769 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.4714. Min Act: -0.0001

Data Index: 124081 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.4352. Min Act: -0.0000

Data Index: 651659 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.4440. Min Act: -0.0001

Data Index: 1040718 (C4 (Web Text))

Max Activating Token Index: 33

Text #8

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.3271. Min Act: -0.0001

Data Index: 607764 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.4600. Min Act: -0.0000

Data Index: 592189 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.4550. Min Act: -0.0000

Data Index: 890934 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.0883. Min Act: -0.0000

Data Index: 1260414 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 4.6634. Min Range: -4.6634

Max Act: 3.7607. Min Act: -0.0000

Data Index: 166232 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.3132. Min Act: -0.0000

Data Index: 302720 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.6249. Min Act: -0.0001

Data Index: 445009 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.1160. Min Act: -0.0000

Data Index: 500167 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.1295. Min Act: -0.0001

Data Index: 265959 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.2287. Min Act: -0.0000

Data Index: 935721 (C4 (Web Text))

Max Activating Token Index: 944

Text #18

Max Range: 4.6634. Min Range: -4.6634

Max Act: 4.1041. Min Act: -0.0001

Data Index: 1097815 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 4.6634. Min Range: -4.6634

Max Act: 3.7846. Min Act: -0.0001

Data Index: 332587 (C4 (Web Text))

Max Activating Token Index: 860