Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2308 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1142. Min Range: -2.1142

Max Act: 2.0549. Min Act: -0.0000

Data Index: 634643 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 2.1142. Min Range: -2.1142

Max Act: 2.1142. Min Act: -0.0000

Data Index: 983346 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.8801. Min Act: -0.0000

Data Index: 916438 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.9317. Min Act: -0.0000

Data Index: 667613 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.8773. Min Act: -0.0001

Data Index: 450497 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.5495. Min Act: -0.0000

Data Index: 32495 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.7268. Min Act: -0.0000

Data Index: 432645 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 2.1142. Min Range: -2.1142

Max Act: 2.0323. Min Act: -0.0000

Data Index: 734419 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.5755. Min Act: -0.0000

Data Index: 587432 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.6835. Min Act: -0.0000

Data Index: 375943 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.8314. Min Act: -0.0000

Data Index: 255888 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.8781. Min Act: -0.0000

Data Index: 841934 (C4 (Web Text))

Max Activating Token Index: 558

Text #12

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.7518. Min Act: -0.0000

Data Index: 975392 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.7648. Min Act: -0.0000

Data Index: 250792 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.7399. Min Act: -0.0000

Data Index: 1250597 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.6646. Min Act: -0.0000

Data Index: 948385 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.7140. Min Act: -0.0000

Data Index: 734065 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.6720. Min Act: -0.0000

Data Index: 907335 (C4 (Web Text))

Max Activating Token Index: 124

Text #18

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.6518. Min Act: -0.0001

Data Index: 485331 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 2.1142. Min Range: -2.1142

Max Act: 1.5993. Min Act: -0.0000

Data Index: 823202 (C4 (Web Text))

Max Activating Token Index: 171