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

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

Neuron 88 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: 0.6470. Min Range: -0.6470

Max Act: 0.6323. Min Act: -0.0000

Data Index: 101121 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.6470. Min Act: -0.0000

Data Index: 595873 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.5566. Min Act: -0.0001

Data Index: 1413750 (Python Code)

Max Activating Token Index: 74

Text #3

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4936. Min Act: -0.0001

Data Index: 1200843 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4903. Min Act: -0.0001

Data Index: 1380766 (Python Code)

Max Activating Token Index: 456

Text #5

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4688. Min Act: -0.0000

Data Index: 713290 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4410. Min Act: -0.0001

Data Index: 293253 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4529. Min Act: -0.0001

Data Index: 356584 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4596. Min Act: -0.0000

Data Index: 58139 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4429. Min Act: -0.0000

Data Index: 264771 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4493. Min Act: -0.0000

Data Index: 755789 (C4 (Web Text))

Max Activating Token Index: 525

Text #11

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4268. Min Act: -0.0001

Data Index: 348319 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.4165. Min Act: -0.0001

Data Index: 1035701 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3955. Min Act: -0.0001

Data Index: 1369197 (Python Code)

Max Activating Token Index: 537

Text #14

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3932. Min Act: -0.0000

Data Index: 260578 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3655. Min Act: -0.0000

Data Index: 81390 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1127553 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3673. Min Act: -0.0000

Data Index: 470006 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3721. Min Act: -0.0000

Data Index: 354937 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.6470. Min Range: -0.6470

Max Act: 0.3566. Min Act: -0.0001

Data Index: 310697 (C4 (Web Text))

Max Activating Token Index: 207