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

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

Neuron 1958 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5153. Min Range: -2.5153

Max Act: 2.5153. Min Act: -0.0000

Data Index: 471848 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 2.5153. Min Range: -2.5153

Max Act: 2.2032. Min Act: -0.0000

Data Index: 601626 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.8810. Min Act: -0.0000

Data Index: 1234598 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.8931. Min Act: -0.0000

Data Index: 47078 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.8644. Min Act: -0.0000

Data Index: 1358090 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.8818. Min Act: -0.0000

Data Index: 1446890 (Python Code)

Max Activating Token Index: 515

Text #6

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.7651. Min Act: -0.0000

Data Index: 1412224 (Python Code)

Max Activating Token Index: 47

Text #7

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.7564. Min Act: -0.0000

Data Index: 1538964 (Python Code)

Max Activating Token Index: 451

Text #8

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.9102. Min Act: -0.0000

Data Index: 1420731 (Python Code)

Max Activating Token Index: 865

Text #9

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.6631. Min Act: -0.0000

Data Index: 1467060 (Python Code)

Max Activating Token Index: 744

Text #10

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.7387. Min Act: -0.0000

Data Index: 1057462 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.5296. Min Act: -0.0000

Data Index: 1582933 (Python Code)

Max Activating Token Index: 984

Text #12

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.5647. Min Act: -0.0000

Data Index: 1400510 (Python Code)

Max Activating Token Index: 854

Text #13

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.4702. Min Act: -0.0000

Data Index: 1449551 (Python Code)

Max Activating Token Index: 805

Text #14

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.6254. Min Act: -0.0000

Data Index: 1516887 (Python Code)

Max Activating Token Index: 265

Text #15

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.5356. Min Act: -0.0000

Data Index: 1445754 (Python Code)

Max Activating Token Index: 261

Text #16

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.5188. Min Act: -0.0000

Data Index: 665721 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.5156. Min Act: -0.0000

Data Index: 386288 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.7649. Min Act: -0.0000

Data Index: 176008 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 2.5153. Min Range: -2.5153

Max Act: 1.4810. Min Act: -0.0000

Data Index: 1390359 (Python Code)

Max Activating Token Index: 563