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

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

Neuron 3067 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: 0.2798. Min Range: -0.2798

Max Act: 0.2798. Min Act: -0.0001

Data Index: 1596802 (Python Code)

Max Activating Token Index: 46

Text #1

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2683. Min Act: -0.0001

Data Index: 1408278 (Python Code)

Max Activating Token Index: 55

Text #2

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2585. Min Act: -0.0002

Data Index: 1366630 (Python Code)

Max Activating Token Index: 717

Text #3

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2574. Min Act: -0.0001

Data Index: 1417090 (Python Code)

Max Activating Token Index: 144

Text #4

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2564. Min Act: -0.0002

Data Index: 1624176 (Python Code)

Max Activating Token Index: 875

Text #5

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2580. Min Act: -0.0001

Data Index: 1448281 (Python Code)

Max Activating Token Index: 847

Text #6

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2532. Min Act: -0.0001

Data Index: 1598532 (Python Code)

Max Activating Token Index: 652

Text #7

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2544. Min Act: -0.0001

Data Index: 1532571 (Python Code)

Max Activating Token Index: 660

Text #8

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2529. Min Act: -0.0002

Data Index: 1408694 (Python Code)

Max Activating Token Index: 906

Text #9

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2565. Min Act: -0.0002

Data Index: 1455348 (Python Code)

Max Activating Token Index: 488

Text #10

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2520. Min Act: -0.0001

Data Index: 1415998 (Python Code)

Max Activating Token Index: 176

Text #11

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2514. Min Act: -0.0001

Data Index: 1571731 (Python Code)

Max Activating Token Index: 245

Text #12

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2508. Min Act: -0.0001

Data Index: 1360873 (Python Code)

Max Activating Token Index: 64

Text #13

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2496. Min Act: -0.0002

Data Index: 1618905 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2493. Min Act: -0.0001

Data Index: 1525432 (Python Code)

Max Activating Token Index: 74

Text #15

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2517. Min Act: -0.0001

Data Index: 1444592 (Python Code)

Max Activating Token Index: 81

Text #16

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2554. Min Act: -0.0001

Data Index: 1427672 (Python Code)

Max Activating Token Index: 828

Text #17

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2479. Min Act: -0.0001

Data Index: 1464560 (Python Code)

Max Activating Token Index: 861

Text #18

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2498. Min Act: -0.0002

Data Index: 1362979 (Python Code)

Max Activating Token Index: 806

Text #19

Max Range: 0.2798. Min Range: -0.2798

Max Act: 0.2517. Min Act: -0.0001

Data Index: 1474405 (Python Code)

Max Activating Token Index: 119