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

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

Neuron 81 in Layer 1

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: 0.9531. Min Range: -0.9531

Max Act: 0.9531. Min Act: -0.0002

Data Index: 1497939 (Python Code)

Max Activating Token Index: 336

Text #1

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9507. Min Act: -0.0002

Data Index: 1632535 (Python Code)

Max Activating Token Index: 97

Text #2

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9344. Min Act: -0.0002

Data Index: 152837 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9224. Min Act: -0.0002

Data Index: 1388225 (Python Code)

Max Activating Token Index: 353

Text #4

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9154. Min Act: -0.0002

Data Index: 1613588 (Python Code)

Max Activating Token Index: 865

Text #5

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8788. Min Act: -0.0002

Data Index: 1497463 (Python Code)

Max Activating Token Index: 88

Text #6

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8872. Min Act: -0.0002

Data Index: 1632641 (Python Code)

Max Activating Token Index: 705

Text #7

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8664. Min Act: -0.0002

Data Index: 1558775 (Python Code)

Max Activating Token Index: 492

Text #8

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8647. Min Act: -0.0002

Data Index: 1485542 (Python Code)

Max Activating Token Index: 216

Text #9

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8519. Min Act: -0.0002

Data Index: 1594957 (Python Code)

Max Activating Token Index: 820

Text #10

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8460. Min Act: -0.0002

Data Index: 1552853 (Python Code)

Max Activating Token Index: 348

Text #11

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8430. Min Act: -0.0002

Data Index: 1518324 (Python Code)

Max Activating Token Index: 660

Text #12

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8570. Min Act: -0.0002

Data Index: 1409422 (Python Code)

Max Activating Token Index: 296

Text #13

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8339. Min Act: -0.0002

Data Index: 1630266 (Python Code)

Max Activating Token Index: 917

Text #14

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8556. Min Act: -0.0002

Data Index: 1376691 (Python Code)

Max Activating Token Index: 150

Text #15

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8393. Min Act: -0.0002

Data Index: 1380388 (Python Code)

Max Activating Token Index: 828

Text #16

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8340. Min Act: -0.0002

Data Index: 1375096 (Python Code)

Max Activating Token Index: 96

Text #17

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8344. Min Act: -0.0002

Data Index: 1475991 (Python Code)

Max Activating Token Index: 26

Text #18

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8417. Min Act: -0.0002

Data Index: 1487684 (Python Code)

Max Activating Token Index: 214

Text #19

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8383. Min Act: -0.0002

Data Index: 1591600 (Python Code)

Max Activating Token Index: 942