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

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

Neuron 3817 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: 0.2240. Min Range: -0.2240

Max Act: 0.2079. Min Act: -0.0000

Data Index: 564592 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2140. Min Act: -0.0000

Data Index: 58066 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2240. Min Act: -0.0000

Data Index: 485813 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2172. Min Act: -0.0000

Data Index: 453288 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.2106. Min Act: -0.0000

Data Index: 702483 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1889. Min Act: -0.0000

Data Index: 67261 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1393065 (Python Code)

Max Activating Token Index: 773

Text #7

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1657. Min Act: -0.0000

Data Index: 1337393 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1833. Min Act: -0.0000

Data Index: 52673 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1801. Min Act: -0.0000

Data Index: 911158 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1293458 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1617. Min Act: -0.0000

Data Index: 1376029 (Python Code)

Max Activating Token Index: 1016

Text #12

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1475. Min Act: -0.0000

Data Index: 1180388 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1765. Min Act: -0.0000

Data Index: 918315 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1086888 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1605. Min Act: -0.0000

Data Index: 250894 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1231968 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1611. Min Act: -0.0000

Data Index: 420150 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1589. Min Act: -0.0000

Data Index: 865211 (C4 (Web Text))

Max Activating Token Index: 507

Text #19

Max Range: 0.2240. Min Range: -0.2240

Max Act: 0.1686. Min Act: -0.0000

Data Index: 897608 (C4 (Web Text))

Max Activating Token Index: 1006