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

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

Neuron 5019 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.9190. Min Act: -0.0000

Data Index: 42204 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.8943. Min Act: -0.0000

Data Index: 46340 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.8082. Min Act: -0.0000

Data Index: 818667 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.9071. Min Act: -0.0000

Data Index: 147847 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.8813. Min Act: -0.0000

Data Index: 43128 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.8694. Min Act: -0.0000

Data Index: 219368 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.8968. Min Act: -0.0000

Data Index: 305291 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 3.0091. Min Range: -3.0091

Max Act: 3.0091. Min Act: -0.0000

Data Index: 432626 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.8494. Min Act: -0.0000

Data Index: 772875 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.9207. Min Act: -0.0000

Data Index: 623624 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.8061. Min Act: -0.0000

Data Index: 46737 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.9344. Min Act: -0.0000

Data Index: 565503 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.5919. Min Act: -0.0000

Data Index: 1005175 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.6072. Min Act: -0.0000

Data Index: 940458 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.4698. Min Act: -0.0000

Data Index: 1117688 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.4611. Min Act: -0.0000

Data Index: 1044735 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.4244. Min Act: -0.0000

Data Index: 1380372 (Python Code)

Max Activating Token Index: 394

Text #17

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.2435. Min Act: -0.0000

Data Index: 230448 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.3679. Min Act: -0.0000

Data Index: 369203 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 3.0091. Min Range: -3.0091

Max Act: 2.3353. Min Act: -0.0000

Data Index: 1055891 (C4 (Web Text))

Max Activating Token Index: 537