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

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

Neuron 709 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: 4.0751. Min Range: -4.0751

Max Act: 4.0751. Min Act: -0.1700

Data Index: 694968 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 4.0751. Min Range: -4.0751

Max Act: 4.0579. Min Act: -0.1700

Data Index: 147208 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.9493. Min Act: -0.1700

Data Index: 452255 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.9536. Min Act: -0.1700

Data Index: 1320092 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 4.0751. Min Range: -4.0751

Max Act: 4.0004. Min Act: -0.1700

Data Index: 26270 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.9305. Min Act: -0.1700

Data Index: 96729 (C4 (Web Text))

Max Activating Token Index: 292

Text #6

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.8612. Min Act: -0.1700

Data Index: 1213093 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.8828. Min Act: -0.1700

Data Index: 1227841 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.9151. Min Act: -0.1700

Data Index: 264416 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.8693. Min Act: -0.1700

Data Index: 342166 (C4 (Web Text))

Max Activating Token Index: 936

Text #10

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.8618. Min Act: -0.1700

Data Index: 40822 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.8843. Min Act: -0.1700

Data Index: 434351 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.8979. Min Act: -0.1700

Data Index: 998724 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.8308. Min Act: -0.1700

Data Index: 1177166 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.8309. Min Act: -0.1700

Data Index: 1311380 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.8510. Min Act: -0.1700

Data Index: 285923 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.8339. Min Act: -0.1700

Data Index: 386342 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.8219. Min Act: -0.1700

Data Index: 3087 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.8699. Min Act: -0.1700

Data Index: 232700 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 4.0751. Min Range: -4.0751

Max Act: 3.8472. Min Act: -0.1700

Data Index: 917866 (C4 (Web Text))

Max Activating Token Index: 224