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

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

Neuron 1159 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: 4.2343. Min Range: -4.2343

Max Act: 4.2343. Min Act: -0.1700

Data Index: 49354 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 4.2343. Min Range: -4.2343

Max Act: 4.0837. Min Act: -0.1700

Data Index: 1263088 (C4 (Web Text))

Max Activating Token Index: 177

Text #2

Max Range: 4.2343. Min Range: -4.2343

Max Act: 4.0489. Min Act: -0.1700

Data Index: 271534 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 4.2343. Min Range: -4.2343

Max Act: 4.0384. Min Act: -0.1700

Data Index: 1169613 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 4.2343. Min Range: -4.2343

Max Act: 4.0425. Min Act: -0.1700

Data Index: 723715 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 4.2343. Min Range: -4.2343

Max Act: 4.0685. Min Act: -0.1700

Data Index: 310784 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 4.2343. Min Range: -4.2343

Max Act: 3.9783. Min Act: -0.1700

Data Index: 1167336 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 4.2343. Min Range: -4.2343

Max Act: 4.0019. Min Act: -0.1700

Data Index: 711267 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 4.2343. Min Range: -4.2343

Max Act: 3.9645. Min Act: -0.1700

Data Index: 196053 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 4.2343. Min Range: -4.2343

Max Act: 3.9531. Min Act: -0.1700

Data Index: 255041 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 4.2343. Min Range: -4.2343

Max Act: 3.9600. Min Act: -0.1700

Data Index: 227287 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 4.2343. Min Range: -4.2343

Max Act: 3.9646. Min Act: -0.1700

Data Index: 963761 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 4.2343. Min Range: -4.2343

Max Act: 3.9577. Min Act: -0.1700

Data Index: 566492 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 4.2343. Min Range: -4.2343

Max Act: 3.9803. Min Act: -0.1700

Data Index: 638694 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 4.2343. Min Range: -4.2343

Max Act: 3.9651. Min Act: -0.1700

Data Index: 656237 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 4.2343. Min Range: -4.2343

Max Act: 3.9522. Min Act: -0.1700

Data Index: 745730 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 4.2343. Min Range: -4.2343

Max Act: 3.9490. Min Act: -0.1700

Data Index: 1106220 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 4.2343. Min Range: -4.2343

Max Act: 3.9451. Min Act: -0.1700

Data Index: 591119 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 4.2343. Min Range: -4.2343

Max Act: 3.9618. Min Act: -0.1700

Data Index: 355671 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 4.2343. Min Range: -4.2343

Max Act: 3.9596. Min Act: -0.1700

Data Index: 480735 (C4 (Web Text))

Max Activating Token Index: 391