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

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

Neuron 1388 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: 3.9446. Min Range: -3.9446

Max Act: 3.9446. Min Act: -0.1700

Data Index: 1407710 (Python Code)

Max Activating Token Index: 317

Text #1

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.7223. Min Act: -0.1700

Data Index: 1572726 (Python Code)

Max Activating Token Index: 348

Text #2

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.6351. Min Act: -0.1697

Data Index: 932089 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.6561. Min Act: -0.1699

Data Index: 1644145 (Python Code)

Max Activating Token Index: 107

Text #4

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.6456. Min Act: -0.1692

Data Index: 1459025 (Python Code)

Max Activating Token Index: 296

Text #5

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.6400. Min Act: -0.1694

Data Index: 7409 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.6265. Min Act: -0.1700

Data Index: 1488224 (Python Code)

Max Activating Token Index: 209

Text #7

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.6391. Min Act: -0.1698

Data Index: 1462097 (Python Code)

Max Activating Token Index: 615

Text #8

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.5933. Min Act: -0.1699

Data Index: 64346 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.5936. Min Act: -0.1693

Data Index: 1465117 (Python Code)

Max Activating Token Index: 976

Text #10

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.5774. Min Act: -0.1273

Data Index: 1512592 (Python Code)

Max Activating Token Index: 313

Text #11

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.6025. Min Act: -0.1689

Data Index: 1418863 (Python Code)

Max Activating Token Index: 801

Text #12

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.5437. Min Act: -0.1700

Data Index: 1578566 (Python Code)

Max Activating Token Index: 669

Text #13

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.5612. Min Act: -0.1700

Data Index: 934281 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.5671. Min Act: -0.1695

Data Index: 924105 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.5671. Min Act: -0.1592

Data Index: 1592775 (Python Code)

Max Activating Token Index: 977

Text #16

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.5512. Min Act: -0.1700

Data Index: 1565499 (Python Code)

Max Activating Token Index: 232

Text #17

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.5720. Min Act: -0.1495

Data Index: 1436897 (Python Code)

Max Activating Token Index: 270

Text #18

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.5462. Min Act: -0.1697

Data Index: 37646 (C4 (Web Text))

Max Activating Token Index: 670

Text #19

Max Range: 3.9446. Min Range: -3.9446

Max Act: 3.5133. Min Act: -0.1700

Data Index: 189710 (C4 (Web Text))

Max Activating Token Index: 374