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

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

Neuron 115 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.1675. Min Act: -0.0000

Data Index: 468435 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.1533. Min Act: -0.0000

Data Index: 168980 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.2860. Min Act: -0.0000

Data Index: 128827 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 5.2860. Min Range: -5.2860

Max Act: 5.0486. Min Act: -0.0000

Data Index: 588381 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.3338. Min Act: -0.0000

Data Index: 1335996 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.8760. Min Act: -0.0000

Data Index: 1153388 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.8869. Min Act: -0.0000

Data Index: 925107 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.8806. Min Act: -0.0000

Data Index: 213961 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.8453. Min Act: -0.0000

Data Index: 617420 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 5.2860. Min Range: -5.2860

Max Act: 3.8150. Min Act: -0.0000

Data Index: 198834 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.4991. Min Act: -0.0000

Data Index: 43890 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.0825. Min Act: -0.0000

Data Index: 959729 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.2631. Min Act: -0.0000

Data Index: 518346 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.3965. Min Act: -0.0000

Data Index: 1042634 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.3719. Min Act: -0.0000

Data Index: 119162 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.3532. Min Act: -0.0000

Data Index: 818307 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.5484. Min Act: -0.0000

Data Index: 876090 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.3282. Min Act: -0.0000

Data Index: 287108 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.2753. Min Act: -0.0000

Data Index: 1241157 (C4 (Web Text))

Max Activating Token Index: 17

Text #19

Max Range: 5.2860. Min Range: -5.2860

Max Act: 4.4170. Min Act: -0.0000

Data Index: 17019 (C4 (Web Text))

Max Activating Token Index: 134