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

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

Neuron 1932 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.6251. Min Act: -0.0001

Data Index: 749327 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.6064. Min Act: -0.0001

Data Index: 1271501 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.5855. Min Act: -0.0001

Data Index: 159801 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.5832. Min Act: -0.0000

Data Index: 1026052 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1271898 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.5686. Min Act: -0.0000

Data Index: 673588 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.5506. Min Act: -0.0000

Data Index: 190875 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.5157. Min Act: -0.0000

Data Index: 855198 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.5436. Min Act: -0.0001

Data Index: 818987 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.5189. Min Act: -0.0001

Data Index: 811765 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.5361. Min Act: -0.0000

Data Index: 856538 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.5379. Min Act: -0.0000

Data Index: 803555 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.5505. Min Act: -0.0000

Data Index: 1331321 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.5369. Min Act: -0.0000

Data Index: 1061949 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.5357. Min Act: -0.0001

Data Index: 696225 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.5151. Min Act: -0.0001

Data Index: 613584 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.5128. Min Act: -0.0001

Data Index: 683552 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4791. Min Act: -0.0000

Data Index: 353424 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.5071. Min Act: -0.0001

Data Index: 206408 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.6251. Min Range: -0.6251

Max Act: 0.4970. Min Act: -0.0000

Data Index: 932069 (C4 (Web Text))

Max Activating Token Index: 243