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

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

Neuron 4660 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: 1.4094. Min Range: -1.4094

Max Act: 1.4094. Min Act: -0.0000

Data Index: 1438065 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.0224. Min Act: -0.0001

Data Index: 1560471 (Python Code)

Max Activating Token Index: 213

Text #2

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.0995. Min Act: -0.0001

Data Index: 608562 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.9646. Min Act: -0.0000

Data Index: 322224 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.9627. Min Act: -0.0001

Data Index: 84424 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 1.4094. Min Range: -1.4094

Max Act: 1.0396. Min Act: -0.0001

Data Index: 723043 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.9027. Min Act: -0.0001

Data Index: 1335052 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.9837. Min Act: -0.0001

Data Index: 954436 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.9789. Min Act: -0.0001

Data Index: 600078 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.8066. Min Act: -0.0001

Data Index: 396192 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.9928. Min Act: -0.0001

Data Index: 14432 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.8942. Min Act: -0.0001

Data Index: 920711 (C4 (Web Text))

Max Activating Token Index: 561

Text #12

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.9333. Min Act: -0.0000

Data Index: 448271 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.9332. Min Act: -0.0001

Data Index: 579331 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.8516. Min Act: -0.0001

Data Index: 720527 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.7976. Min Act: -0.0000

Data Index: 71779 (C4 (Web Text))

Max Activating Token Index: 363

Text #16

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.7907. Min Act: -0.0001

Data Index: 248169 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.7747. Min Act: -0.0001

Data Index: 179388 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.8993. Min Act: -0.0001

Data Index: 66445 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 1.4094. Min Range: -1.4094

Max Act: 0.8692. Min Act: -0.0001

Data Index: 1208675 (C4 (Web Text))

Max Activating Token Index: 563