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

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

Neuron 477 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: 3.1340. Min Range: -3.1340

Max Act: 3.1335. Min Act: -0.1700

Data Index: 908737 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.1340. Min Act: -0.1692

Data Index: 542626 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.1324. Min Act: -0.1700

Data Index: 37127 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.0969. Min Act: -0.1697

Data Index: 457062 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.0944. Min Act: -0.1695

Data Index: 216426 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.0863. Min Act: -0.1699

Data Index: 144129 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.1000. Min Act: -0.1690

Data Index: 112220 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.0907. Min Act: -0.1700

Data Index: 694828 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.0723. Min Act: -0.1687

Data Index: 96040 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.0893. Min Act: -0.1699

Data Index: 624540 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.0755. Min Act: -0.1700

Data Index: 332424 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.0643. Min Act: -0.1699

Data Index: 518576 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.0594. Min Act: -0.1688

Data Index: 1227195 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.0604. Min Act: -0.1699

Data Index: 25625 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.0611. Min Act: -0.1700

Data Index: 291175 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.0592. Min Act: -0.1698

Data Index: 507130 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.0526. Min Act: -0.1700

Data Index: 984660 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.0137. Min Act: -0.1700

Data Index: 845708 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.0239. Min Act: -0.1700

Data Index: 746678 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 3.1340. Min Range: -3.1340

Max Act: 3.0346. Min Act: -0.1700

Data Index: 1026948 (C4 (Web Text))

Max Activating Token Index: 13