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

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

Neuron 5312 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.7544. Min Act: -0.0001

Data Index: 839613 (C4 (Web Text))

Max Activating Token Index: 925

Text #1

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.5229. Min Act: -0.0001

Data Index: 258111 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.5532. Min Act: -0.0001

Data Index: 494987 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.1723. Min Act: -0.0000

Data Index: 1039171 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.4556. Min Act: -0.0000

Data Index: 1011573 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.2340. Min Act: -0.0000

Data Index: 47397 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.2662. Min Act: -0.0000

Data Index: 538802 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.2750. Min Act: -0.0000

Data Index: 1211295 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.1514. Min Act: -0.0000

Data Index: 859939 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.3411. Min Act: -0.0000

Data Index: 991569 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.3351. Min Act: -0.0000

Data Index: 284994 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.2576. Min Act: -0.0001

Data Index: 1264044 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.0961. Min Act: -0.0000

Data Index: 664809 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.1124. Min Act: -0.0000

Data Index: 534941 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.1046. Min Act: -0.0001

Data Index: 515985 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 2.7544. Min Range: -2.7544

Max Act: 1.8873. Min Act: -0.0000

Data Index: 300622 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.0616. Min Act: -0.0000

Data Index: 376321 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 2.7544. Min Range: -2.7544

Max Act: 1.9265. Min Act: -0.0001

Data Index: 1006924 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.3823. Min Act: -0.0000

Data Index: 1181175 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 2.7544. Min Range: -2.7544

Max Act: 2.1913. Min Act: -0.0001

Data Index: 1072262 (C4 (Web Text))

Max Activating Token Index: 404