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

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

Neuron 573 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.9284. Min Act: -0.0000

Data Index: 1301821 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.9185. Min Act: -0.0000

Data Index: 1099201 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.8081. Min Act: -0.0000

Data Index: 858028 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.7729. Min Act: -0.0000

Data Index: 853011 (C4 (Web Text))

Max Activating Token Index: 932

Text #4

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.8273. Min Act: -0.0001

Data Index: 1071609 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.7716. Min Act: -0.0000

Data Index: 976574 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.7526. Min Act: -0.0000

Data Index: 822207 (C4 (Web Text))

Max Activating Token Index: 161

Text #7

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.8070. Min Act: -0.0000

Data Index: 528757 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6365. Min Act: -0.0000

Data Index: 245604 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6802. Min Act: -0.0000

Data Index: 450960 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.7184. Min Act: -0.0000

Data Index: 326475 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6456. Min Act: -0.0000

Data Index: 873726 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6010. Min Act: -0.0001

Data Index: 552774 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6594. Min Act: -0.0000

Data Index: 807167 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6036. Min Act: -0.0000

Data Index: 813090 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.5951. Min Act: -0.0000

Data Index: 1080420 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6038. Min Act: -0.0000

Data Index: 1264600 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6489. Min Act: -0.0000

Data Index: 198115 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.5575. Min Act: -0.0000

Data Index: 1172030 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 1.9284. Min Range: -1.9284

Max Act: 1.6070. Min Act: -0.0000

Data Index: 1130588 (C4 (Web Text))

Max Activating Token Index: 104