Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1601 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.0554. Min Range: -7.0554

Max Act: 7.0554. Min Act: -0.1700

Data Index: 1040607 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.8679. Min Act: -0.1700

Data Index: 1219848 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.6804. Min Act: -0.1700

Data Index: 239157 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.6179. Min Act: -0.1699

Data Index: 149825 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.6179. Min Act: -0.1700

Data Index: 5784 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.4929. Min Act: -0.1700

Data Index: 206751 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.6179. Min Act: -0.1700

Data Index: 1015203 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.6179. Min Act: -0.1700

Data Index: 559607 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.4616. Min Act: -0.1700

Data Index: 1294203 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.4616. Min Act: -0.1700

Data Index: 1262028 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.4616. Min Act: -0.1700

Data Index: 1234930 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.5241. Min Act: -0.1699

Data Index: 997113 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.5241. Min Act: -0.1700

Data Index: 806776 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.4616. Min Act: -0.1700

Data Index: 880651 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.4304. Min Act: -0.1700

Data Index: 1159810 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.4616. Min Act: -0.1700

Data Index: 1086714 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.4616. Min Act: -0.1700

Data Index: 557905 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.4304. Min Act: -0.1700

Data Index: 95219 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.3366. Min Act: -0.1700

Data Index: 781262 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 7.0554. Min Range: -7.0554

Max Act: 6.3054. Min Act: -0.1700

Data Index: 575496 (C4 (Web Text))

Max Activating Token Index: 845