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

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

Neuron 3715 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.8549. Min Act: -0.0000

Data Index: 536601 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.5119. Min Act: -0.0000

Data Index: 1058244 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 5.8549. Min Range: -5.8549

Max Act: 5.2590. Min Act: -0.0000

Data Index: 866693 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.8589. Min Act: -0.0000

Data Index: 347864 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.7071. Min Act: -0.0000

Data Index: 21659 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.6979. Min Act: -0.0000

Data Index: 474742 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.6154. Min Act: -0.0000

Data Index: 1163068 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.3079. Min Act: -0.0000

Data Index: 1296618 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.4455. Min Act: -0.0000

Data Index: 372358 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.2578. Min Act: -0.0000

Data Index: 457327 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.5801. Min Act: -0.0000

Data Index: 1010793 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.5396. Min Act: -0.0000

Data Index: 1316032 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.3409. Min Act: -0.0000

Data Index: 262287 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.3465. Min Act: -0.0000

Data Index: 1347082 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.3061. Min Act: -0.0000

Data Index: 835013 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.3044. Min Act: -0.0000

Data Index: 1216210 (C4 (Web Text))

Max Activating Token Index: 663

Text #16

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.4244. Min Act: -0.0000

Data Index: 504003 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.3970. Min Act: -0.0000

Data Index: 1172582 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.2628. Min Act: -0.0000

Data Index: 1145243 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 5.8549. Min Range: -5.8549

Max Act: 4.0285. Min Act: -0.0000

Data Index: 517965 (C4 (Web Text))

Max Activating Token Index: 81