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

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

Neuron 1220 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.7786. Min Act: -0.0000

Data Index: 397439 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.7335. Min Act: -0.0000

Data Index: 250390 (C4 (Web Text))

Max Activating Token Index: 478

Text #2

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.7108. Min Act: -0.0000

Data Index: 449244 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6714. Min Act: -0.0000

Data Index: 1045529 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6761. Min Act: -0.0000

Data Index: 353466 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1173832 (C4 (Web Text))

Max Activating Token Index: 212

Text #6

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6592. Min Act: -0.0000

Data Index: 168610 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6963. Min Act: -0.0000

Data Index: 675659 (C4 (Web Text))

Max Activating Token Index: 225

Text #8

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6541. Min Act: -0.0000

Data Index: 421095 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6330. Min Act: -0.0000

Data Index: 390778 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6962. Min Act: -0.0000

Data Index: 445967 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6436. Min Act: -0.0000

Data Index: 173030 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6447. Min Act: -0.0000

Data Index: 328875 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1097915 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6859. Min Act: -0.0000

Data Index: 697563 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6569. Min Act: -0.0000

Data Index: 488264 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6187. Min Act: -0.0000

Data Index: 139960 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6296. Min Act: -0.0000

Data Index: 673147 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6059. Min Act: -0.0000

Data Index: 311970 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.7786. Min Range: -0.7786

Max Act: 0.6775. Min Act: -0.0000

Data Index: 1248186 (C4 (Web Text))

Max Activating Token Index: 844