Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1071 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.1724. Min Range: -4.1724

Max Act: 4.1724. Min Act: -0.1700

Data Index: 1520842 (Python Code)

Max Activating Token Index: 413

Text #1

Max Range: 4.1724. Min Range: -4.1724

Max Act: 4.1004. Min Act: -0.1700

Data Index: 1499122 (Python Code)

Max Activating Token Index: 613

Text #2

Max Range: 4.1724. Min Range: -4.1724

Max Act: 4.0482. Min Act: -0.1700

Data Index: 1359937 (Python Code)

Max Activating Token Index: 834

Text #3

Max Range: 4.1724. Min Range: -4.1724

Max Act: 4.0552. Min Act: -0.1700

Data Index: 605609 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 4.1724. Min Range: -4.1724

Max Act: 4.0450. Min Act: -0.1700

Data Index: 1504295 (Python Code)

Max Activating Token Index: 637

Text #5

Max Range: 4.1724. Min Range: -4.1724

Max Act: 3.9845. Min Act: -0.1700

Data Index: 874993 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 4.1724. Min Range: -4.1724

Max Act: 4.0129. Min Act: -0.1700

Data Index: 1651969 (Python Code)

Max Activating Token Index: 199

Text #7

Max Range: 4.1724. Min Range: -4.1724

Max Act: 3.9770. Min Act: -0.1700

Data Index: 1490296 (Python Code)

Max Activating Token Index: 107

Text #8

Max Range: 4.1724. Min Range: -4.1724

Max Act: 3.9633. Min Act: -0.1700

Data Index: 1371893 (Python Code)

Max Activating Token Index: 315

Text #9

Max Range: 4.1724. Min Range: -4.1724

Max Act: 3.9645. Min Act: -0.1700

Data Index: 1611558 (Python Code)

Max Activating Token Index: 767

Text #10

Max Range: 4.1724. Min Range: -4.1724

Max Act: 3.9700. Min Act: -0.1700

Data Index: 1406701 (Python Code)

Max Activating Token Index: 358

Text #11

Max Range: 4.1724. Min Range: -4.1724

Max Act: 3.9435. Min Act: -0.1700

Data Index: 1520107 (Python Code)

Max Activating Token Index: 87

Text #12

Max Range: 4.1724. Min Range: -4.1724

Max Act: 3.9346. Min Act: -0.1700

Data Index: 625248 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 4.1724. Min Range: -4.1724

Max Act: 3.9360. Min Act: -0.1700

Data Index: 927414 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 4.1724. Min Range: -4.1724

Max Act: 3.9218. Min Act: -0.1700

Data Index: 1640359 (Python Code)

Max Activating Token Index: 402

Text #15

Max Range: 4.1724. Min Range: -4.1724

Max Act: 3.9347. Min Act: -0.1700

Data Index: 1361898 (Python Code)

Max Activating Token Index: 528

Text #16

Max Range: 4.1724. Min Range: -4.1724

Max Act: 3.9071. Min Act: -0.1700

Data Index: 1366713 (Python Code)

Max Activating Token Index: 84

Text #17

Max Range: 4.1724. Min Range: -4.1724

Max Act: 3.8774. Min Act: -0.1700

Data Index: 611831 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 4.1724. Min Range: -4.1724

Max Act: 3.9126. Min Act: -0.1700

Data Index: 604069 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 4.1724. Min Range: -4.1724

Max Act: 3.9008. Min Act: -0.1700

Data Index: 618081 (C4 (Web Text))

Max Activating Token Index: 741