Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4317 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.5989. Min Act: -0.0000

Data Index: 755652 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.5205. Min Act: -0.0000

Data Index: 632135 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.3566. Min Act: -0.0000

Data Index: 541303 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.2525. Min Act: -0.0000

Data Index: 518886 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.2728. Min Act: -0.0000

Data Index: 1080081 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.2632. Min Act: -0.0000

Data Index: 594540 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.2423. Min Act: -0.0000

Data Index: 889852 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.2906. Min Act: -0.0000

Data Index: 647228 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.1850. Min Act: -0.0000

Data Index: 1262662 (C4 (Web Text))

Max Activating Token Index: 367

Text #9

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.1680. Min Act: -0.0000

Data Index: 612960 (C4 (Web Text))

Max Activating Token Index: 619

Text #10

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.1863. Min Act: -0.0000

Data Index: 999780 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.1463. Min Act: -0.0000

Data Index: 974622 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.0867. Min Act: -0.0000

Data Index: 1065738 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.1700. Min Act: -0.0000

Data Index: 266673 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.0993. Min Act: -0.0000

Data Index: 453233 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.0229. Min Act: -0.0000

Data Index: 873617 (C4 (Web Text))

Max Activating Token Index: 592

Text #16

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.0511. Min Act: -0.0000

Data Index: 483414 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 1.5989. Min Range: -1.5989

Max Act: 0.9854. Min Act: -0.0000

Data Index: 534368 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.0341. Min Act: -0.0000

Data Index: 1183093 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 1.5989. Min Range: -1.5989

Max Act: 1.0546. Min Act: -0.0000

Data Index: 891542 (C4 (Web Text))

Max Activating Token Index: 211