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

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

Neuron 1774 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: 3.9973. Min Range: -3.9973

Max Act: 3.9973. Min Act: -0.1700

Data Index: 38577 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.8787. Min Act: -0.1700

Data Index: 361743 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.8854. Min Act: -0.1700

Data Index: 778802 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.8648. Min Act: -0.1700

Data Index: 700659 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.8589. Min Act: -0.1700

Data Index: 72226 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.8195. Min Act: -0.1700

Data Index: 184055 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.8104. Min Act: -0.1700

Data Index: 770751 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.7871. Min Act: -0.1700

Data Index: 1290326 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.7844. Min Act: -0.1700

Data Index: 524108 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.7857. Min Act: -0.1700

Data Index: 259226 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.7901. Min Act: -0.1699

Data Index: 839135 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.7578. Min Act: -0.1700

Data Index: 299238 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.7726. Min Act: -0.1700

Data Index: 688891 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.7694. Min Act: -0.1700

Data Index: 1023697 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.7331. Min Act: -0.1700

Data Index: 200157 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.7311. Min Act: -0.1700

Data Index: 1301035 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.7078. Min Act: -0.1700

Data Index: 1068443 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.7054. Min Act: -0.1700

Data Index: 1058041 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.6946. Min Act: -0.1700

Data Index: 341162 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 3.9973. Min Range: -3.9973

Max Act: 3.6934. Min Act: -0.1700

Data Index: 893507 (C4 (Web Text))

Max Activating Token Index: 437