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

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

Neuron 721 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: 1.4914. Min Range: -1.4914

Max Act: 1.4914. Min Act: -0.0000

Data Index: 856270 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.2323. Min Act: -0.0001

Data Index: 1271709 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.1019. Min Act: -0.0001

Data Index: 647035 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.0255. Min Act: -0.0000

Data Index: 163228 (C4 (Web Text))

Max Activating Token Index: 776

Text #4

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.0336. Min Act: -0.0000

Data Index: 672080 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.0586. Min Act: -0.0000

Data Index: 85489 (C4 (Web Text))

Max Activating Token Index: 348

Text #6

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.0683. Min Act: -0.0001

Data Index: 711154 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.0290. Min Act: -0.0000

Data Index: 448060 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 1.4914. Min Range: -1.4914

Max Act: 0.9831. Min Act: -0.0000

Data Index: 1057007 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.0003. Min Act: -0.0001

Data Index: 1093356 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 1.4914. Min Range: -1.4914

Max Act: 0.9566. Min Act: -0.0000

Data Index: 941507 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 1.4914. Min Range: -1.4914

Max Act: 0.9823. Min Act: -0.0000

Data Index: 69408 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 1.4914. Min Range: -1.4914

Max Act: 0.9756. Min Act: -0.0000

Data Index: 271249 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 1.4914. Min Range: -1.4914

Max Act: 0.9663. Min Act: -0.0001

Data Index: 857040 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 1.4914. Min Range: -1.4914

Max Act: 0.9683. Min Act: -0.0000

Data Index: 525953 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 1.4914. Min Range: -1.4914

Max Act: 0.9701. Min Act: -0.0000

Data Index: 464062 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 1.4914. Min Range: -1.4914

Max Act: 0.9954. Min Act: -0.0001

Data Index: 152142 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 1.4914. Min Range: -1.4914

Max Act: 0.9882. Min Act: -0.0000

Data Index: 585816 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 1.4914. Min Range: -1.4914

Max Act: 0.9166. Min Act: -0.0001

Data Index: 941953 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 1.4914. Min Range: -1.4914

Max Act: 0.9701. Min Act: -0.0001

Data Index: 220233 (C4 (Web Text))

Max Activating Token Index: 1014