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

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

Neuron 1381 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: 4.8466. Min Range: -4.8466

Max Act: 4.8466. Min Act: -0.1700

Data Index: 1080819 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.7825. Min Act: -0.1700

Data Index: 134079 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.7344. Min Act: -0.1700

Data Index: 1082248 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.7203. Min Act: -0.1700

Data Index: 92875 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.6907. Min Act: -0.1700

Data Index: 1078858 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.6979. Min Act: -0.1700

Data Index: 119058 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.7110. Min Act: -0.1700

Data Index: 1347693 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.6816. Min Act: -0.1700

Data Index: 593741 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.6683. Min Act: -0.1700

Data Index: 1062932 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.6515. Min Act: -0.1700

Data Index: 885175 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.6285. Min Act: -0.1700

Data Index: 552883 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.6605. Min Act: -0.1700

Data Index: 480517 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.6383. Min Act: -0.1700

Data Index: 676646 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.6264. Min Act: -0.1700

Data Index: 1124311 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.6378. Min Act: -0.1700

Data Index: 183249 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.6385. Min Act: -0.1700

Data Index: 169577 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.6347. Min Act: -0.1700

Data Index: 185701 (C4 (Web Text))

Max Activating Token Index: 736

Text #17

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.6760. Min Act: -0.1700

Data Index: 797386 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.6583. Min Act: -0.1700

Data Index: 576255 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 4.8466. Min Range: -4.8466

Max Act: 4.6561. Min Act: -0.1700

Data Index: 1073082 (C4 (Web Text))

Max Activating Token Index: 549