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

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

Neuron 1871 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: 2.0694. Min Range: -2.0694

Max Act: 2.0694. Min Act: -0.0000

Data Index: 336721 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 2.0694. Min Range: -2.0694

Max Act: 2.0300. Min Act: -0.0000

Data Index: 583124 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.9152. Min Act: -0.0000

Data Index: 9951 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.8165. Min Act: -0.0000

Data Index: 61069 (C4 (Web Text))

Max Activating Token Index: 1009

Text #4

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.8052. Min Act: -0.0000

Data Index: 1356981 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.8969. Min Act: -0.0000

Data Index: 1102182 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.7847. Min Act: -0.0000

Data Index: 333991 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.8750. Min Act: -0.0000

Data Index: 134593 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.8521. Min Act: -0.0000

Data Index: 583408 (C4 (Web Text))

Max Activating Token Index: 157

Text #9

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.8080. Min Act: -0.0000

Data Index: 481991 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.8079. Min Act: -0.0000

Data Index: 643389 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.7794. Min Act: -0.0000

Data Index: 667006 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.7683. Min Act: -0.0000

Data Index: 1302630 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.7588. Min Act: -0.0000

Data Index: 316445 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.7342. Min Act: -0.0000

Data Index: 385522 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.7250. Min Act: -0.0000

Data Index: 1146576 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.6077. Min Act: -0.0000

Data Index: 296584 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.6811. Min Act: -0.0000

Data Index: 1343481 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.6717. Min Act: -0.0000

Data Index: 654961 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 2.0694. Min Range: -2.0694

Max Act: 1.4806. Min Act: -0.0000

Data Index: 509591 (C4 (Web Text))

Max Activating Token Index: 305