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

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

Neuron 1758 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: 1.7998. Min Range: -1.7998

Max Act: 1.7998. Min Act: -0.0001

Data Index: 13596 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.4777. Min Act: -0.0001

Data Index: 767011 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.5578. Min Act: -0.0001

Data Index: 818842 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.5475. Min Act: -0.0000

Data Index: 532917 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.3810. Min Act: -0.0001

Data Index: 690606 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.5871. Min Act: -0.0001

Data Index: 419714 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.4141. Min Act: -0.0001

Data Index: 552233 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.4062. Min Act: -0.0001

Data Index: 1148941 (C4 (Web Text))

Max Activating Token Index: 568

Text #8

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.4112. Min Act: -0.0000

Data Index: 647143 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.3920. Min Act: -0.0000

Data Index: 355691 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.4432. Min Act: -0.0001

Data Index: 22038 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.3592. Min Act: -0.0000

Data Index: 178673 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.2031. Min Act: -0.0001

Data Index: 561622 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.3902. Min Act: -0.0001

Data Index: 1059191 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.2032. Min Act: -0.0000

Data Index: 542590 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.4075. Min Act: -0.0000

Data Index: 762274 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.4216. Min Act: -0.0001

Data Index: 564695 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.4003. Min Act: -0.0000

Data Index: 259798 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.3566. Min Act: -0.0000

Data Index: 423423 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 1.7998. Min Range: -1.7998

Max Act: 1.2826. Min Act: -0.0001

Data Index: 677347 (C4 (Web Text))

Max Activating Token Index: 858