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

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

Neuron 5649 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: 1.6464. Min Range: -1.6464

Max Act: 1.6275. Min Act: -0.0002

Data Index: 1610521 (Python Code)

Max Activating Token Index: 769

Text #1

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.6464. Min Act: -0.0002

Data Index: 1396842 (Python Code)

Max Activating Token Index: 784

Text #2

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.6105. Min Act: -0.0002

Data Index: 1492056 (Python Code)

Max Activating Token Index: 500

Text #3

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.5634. Min Act: -0.0002

Data Index: 1519682 (Python Code)

Max Activating Token Index: 782

Text #4

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.5989. Min Act: -0.0002

Data Index: 1505784 (Python Code)

Max Activating Token Index: 867

Text #5

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.5747. Min Act: -0.0002

Data Index: 1464047 (Python Code)

Max Activating Token Index: 585

Text #6

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.6097. Min Act: -0.0002

Data Index: 1524388 (Python Code)

Max Activating Token Index: 471

Text #7

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.5166. Min Act: -0.0002

Data Index: 1498442 (Python Code)

Max Activating Token Index: 436

Text #8

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.4725. Min Act: -0.0002

Data Index: 1496149 (Python Code)

Max Activating Token Index: 717

Text #9

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.4791. Min Act: -0.0002

Data Index: 1654900 (Python Code)

Max Activating Token Index: 703

Text #10

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.4882. Min Act: -0.0002

Data Index: 1535404 (Python Code)

Max Activating Token Index: 706

Text #11

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.4408. Min Act: -0.0002

Data Index: 1556123 (Python Code)

Max Activating Token Index: 791

Text #12

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.4772. Min Act: -0.0002

Data Index: 1646793 (Python Code)

Max Activating Token Index: 712

Text #13

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.4392. Min Act: -0.0002

Data Index: 1521623 (Python Code)

Max Activating Token Index: 761

Text #14

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.4277. Min Act: -0.0002

Data Index: 1637084 (Python Code)

Max Activating Token Index: 746

Text #15

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.4698. Min Act: -0.0002

Data Index: 1368759 (Python Code)

Max Activating Token Index: 803

Text #16

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.4334. Min Act: -0.0002

Data Index: 1640749 (Python Code)

Max Activating Token Index: 720

Text #17

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.4656. Min Act: -0.0002

Data Index: 1506932 (Python Code)

Max Activating Token Index: 841

Text #18

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.4293. Min Act: -0.0002

Data Index: 1650117 (Python Code)

Max Activating Token Index: 293

Text #19

Max Range: 1.6464. Min Range: -1.6464

Max Act: 1.4267. Min Act: -0.0002

Data Index: 1511304 (Python Code)

Max Activating Token Index: 689