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

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

Neuron 1214 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1712. Min Act: -0.0001

Data Index: 659792 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1312. Min Act: -0.0001

Data Index: 239667 (C4 (Web Text))

Max Activating Token Index: 189

Text #2

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1116. Min Act: -0.0001

Data Index: 884611 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1042223 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1155. Min Act: -0.0001

Data Index: 907264 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1104. Min Act: -0.0001

Data Index: 704567 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1036. Min Act: -0.0001

Data Index: 1470054 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0912. Min Act: -0.0001

Data Index: 253534 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0904. Min Act: -0.0001

Data Index: 637941 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0931. Min Act: -0.0001

Data Index: 57402 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0913. Min Act: -0.0001

Data Index: 330190 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0900. Min Act: -0.0001

Data Index: 830730 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0900. Min Act: -0.0001

Data Index: 727563 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0826. Min Act: -0.0001

Data Index: 575540 (C4 (Web Text))

Max Activating Token Index: 504

Text #14

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0849. Min Act: -0.0001

Data Index: 1522064 (Python Code)

Max Activating Token Index: 162

Text #15

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0804. Min Act: -0.0001

Data Index: 674000 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0849. Min Act: -0.0001

Data Index: 736900 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0828. Min Act: -0.0001

Data Index: 199070 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0795. Min Act: -0.0001

Data Index: 906407 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.0784. Min Act: -0.0001

Data Index: 299075 (C4 (Web Text))

Max Activating Token Index: 128