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

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

Neuron 4000 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: 3.1568. Min Range: -3.1568

Max Act: 3.1568. Min Act: -0.0000

Data Index: 1117956 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 3.1568. Min Range: -3.1568

Max Act: 2.9665. Min Act: -0.0000

Data Index: 642227 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 3.1568. Min Range: -3.1568

Max Act: 3.1193. Min Act: -0.0000

Data Index: 486489 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 3.1568. Min Range: -3.1568

Max Act: 3.0599. Min Act: -0.0000

Data Index: 275767 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 3.1568. Min Range: -3.1568

Max Act: 2.9913. Min Act: -0.0000

Data Index: 1233047 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 3.1568. Min Range: -3.1568

Max Act: 2.9769. Min Act: -0.0000

Data Index: 530091 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 3.1568. Min Range: -3.1568

Max Act: 2.9721. Min Act: -0.0000

Data Index: 495078 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 3.1568. Min Range: -3.1568

Max Act: 3.0918. Min Act: -0.0000

Data Index: 386218 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 3.1568. Min Range: -3.1568

Max Act: 2.9461. Min Act: -0.0000

Data Index: 649037 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 3.1568. Min Range: -3.1568

Max Act: 2.3990. Min Act: -0.0000

Data Index: 948036 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 3.1568. Min Range: -3.1568

Max Act: 2.1552. Min Act: -0.0000

Data Index: 698435 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 3.1568. Min Range: -3.1568

Max Act: 2.1626. Min Act: -0.0000

Data Index: 337548 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 3.1568. Min Range: -3.1568

Max Act: 2.2633. Min Act: -0.0000

Data Index: 521099 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 3.1568. Min Range: -3.1568

Max Act: 2.2584. Min Act: -0.0000

Data Index: 544114 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 3.1568. Min Range: -3.1568

Max Act: 2.2656. Min Act: -0.0000

Data Index: 767177 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 3.1568. Min Range: -3.1568

Max Act: 2.2785. Min Act: -0.0000

Data Index: 1016220 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 3.1568. Min Range: -3.1568

Max Act: 2.2146. Min Act: -0.0000

Data Index: 1132244 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 3.1568. Min Range: -3.1568

Max Act: 2.1518. Min Act: -0.0000

Data Index: 28028 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 3.1568. Min Range: -3.1568

Max Act: 1.7986. Min Act: -0.0000

Data Index: 159324 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 3.1568. Min Range: -3.1568

Max Act: 1.8444. Min Act: -0.0000

Data Index: 323203 (C4 (Web Text))

Max Activating Token Index: 460