Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 921 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0622. Min Act: -0.0001

Data Index: 681689 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0581. Min Act: -0.0001

Data Index: 487584 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1505430 (Python Code)

Max Activating Token Index: 297

Text #3

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0568. Min Act: -0.0001

Data Index: 485264 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1490198 (Python Code)

Max Activating Token Index: 27

Text #5

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0552. Min Act: -0.0001

Data Index: 554568 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1241562 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0546. Min Act: -0.0001

Data Index: 1521503 (Python Code)

Max Activating Token Index: 560

Text #8

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1508291 (Python Code)

Max Activating Token Index: 617

Text #9

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0538. Min Act: -0.0001

Data Index: 68771 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0540. Min Act: -0.0001

Data Index: 1621952 (Python Code)

Max Activating Token Index: 155

Text #11

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0546. Min Act: -0.0001

Data Index: 236223 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0536. Min Act: -0.0001

Data Index: 1180881 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0543. Min Act: -0.0001

Data Index: 1493335 (Python Code)

Max Activating Token Index: 625

Text #14

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0544. Min Act: -0.0001

Data Index: 789099 (C4 (Web Text))

Max Activating Token Index: 990

Text #15

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0533. Min Act: -0.0001

Data Index: 642847 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0529. Min Act: -0.0001

Data Index: 378920 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1365893 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1457189 (Python Code)

Max Activating Token Index: 375

Text #19

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1628868 (Python Code)

Max Activating Token Index: 34