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

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

Neuron 1158 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.7393. Min Act: -0.0000

Data Index: 1475890 (Python Code)

Max Activating Token Index: 460

Text #1

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.7554. Min Act: -0.0000

Data Index: 1461874 (Python Code)

Max Activating Token Index: 690

Text #2

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.7051. Min Act: -0.0000

Data Index: 931292 (C4 (Web Text))

Max Activating Token Index: 176

Text #3

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6862. Min Act: -0.0000

Data Index: 100017 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6709. Min Act: -0.0000

Data Index: 754925 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6344. Min Act: -0.0000

Data Index: 343679 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1156962 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6579. Min Act: -0.0000

Data Index: 481524 (C4 (Web Text))

Max Activating Token Index: 746

Text #8

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6392. Min Act: -0.0000

Data Index: 119491 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6514. Min Act: -0.0000

Data Index: 8974 (C4 (Web Text))

Max Activating Token Index: 730

Text #10

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6523. Min Act: -0.0000

Data Index: 824961 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6131. Min Act: -0.0000

Data Index: 92515 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6012. Min Act: -0.0001

Data Index: 1416511 (Python Code)

Max Activating Token Index: 867

Text #13

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5720. Min Act: -0.0000

Data Index: 724802 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5507. Min Act: -0.0000

Data Index: 287279 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1040830 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6086. Min Act: -0.0000

Data Index: 471289 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5939. Min Act: -0.0000

Data Index: 1543719 (Python Code)

Max Activating Token Index: 844

Text #18

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5764. Min Act: -0.0000

Data Index: 79102 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6463. Min Act: -0.0000

Data Index: 1455043 (Python Code)

Max Activating Token Index: 104