Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 500 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1864. Min Range: -1.1864

Max Act: 1.1864. Min Act: -0.0001

Data Index: 336123 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.7345. Min Act: -0.0001

Data Index: 72439 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.7506. Min Act: -0.0001

Data Index: 1051995 (C4 (Web Text))

Max Activating Token Index: 235

Text #3

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.7154. Min Act: -0.0001

Data Index: 193081 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.7521. Min Act: -0.0001

Data Index: 628566 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.6972. Min Act: -0.0001

Data Index: 724511 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.7138. Min Act: -0.0001

Data Index: 666041 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.7337. Min Act: -0.0001

Data Index: 1228602 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.6840. Min Act: -0.0001

Data Index: 493445 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.7055. Min Act: -0.0001

Data Index: 373869 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.6812. Min Act: -0.0001

Data Index: 1126533 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.7245. Min Act: -0.0001

Data Index: 1107331 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.6761. Min Act: -0.0001

Data Index: 158240 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.7142. Min Act: -0.0001

Data Index: 1262429 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.6911. Min Act: -0.0001

Data Index: 24910 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.6788. Min Act: -0.0001

Data Index: 435245 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.6786. Min Act: -0.0001

Data Index: 1285959 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.6757. Min Act: -0.0001

Data Index: 1247517 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.6663. Min Act: -0.0001

Data Index: 82572 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 1.1864. Min Range: -1.1864

Max Act: 0.6475. Min Act: -0.0001

Data Index: 145305 (C4 (Web Text))

Max Activating Token Index: 73