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

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

Neuron 3532 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: 1.1270. Min Range: -1.1270

Max Act: 1.1270. Min Act: -0.0001

Data Index: 367182 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 1.1270. Min Range: -1.1270

Max Act: 1.0169. Min Act: -0.0000

Data Index: 419896 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.9341. Min Act: -0.0000

Data Index: 308552 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.9723. Min Act: -0.0000

Data Index: 6517 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.9356. Min Act: -0.0001

Data Index: 830785 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1020797 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.8457. Min Act: -0.0000

Data Index: 902963 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.7908. Min Act: -0.0000

Data Index: 842774 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.7801. Min Act: -0.0000

Data Index: 384148 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.7839. Min Act: -0.0001

Data Index: 673685 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1308427 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.7478. Min Act: -0.0001

Data Index: 878353 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.7939. Min Act: -0.0000

Data Index: 53128 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.7544. Min Act: -0.0001

Data Index: 628122 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.8219. Min Act: -0.0000

Data Index: 522392 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.7456. Min Act: -0.0001

Data Index: 774811 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.7273. Min Act: -0.0000

Data Index: 660861 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.6775. Min Act: -0.0001

Data Index: 1026462 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.7196. Min Act: -0.0000

Data Index: 1288915 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 1.1270. Min Range: -1.1270

Max Act: 0.7173. Min Act: -0.0001

Data Index: 1340708 (C4 (Web Text))

Max Activating Token Index: 669