Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1431 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.0491. Min Range: -5.0491

Max Act: 5.0491. Min Act: -0.1700

Data Index: 1297168 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.9866. Min Act: -0.1700

Data Index: 792456 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 5.0491. Min Range: -5.0491

Max Act: 5.0179. Min Act: -0.1700

Data Index: 82286 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.9241. Min Act: -0.1700

Data Index: 396654 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.8929. Min Act: -0.1700

Data Index: 159381 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.8929. Min Act: -0.1700

Data Index: 468495 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.8616. Min Act: -0.1700

Data Index: 170008 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.8616. Min Act: -0.1700

Data Index: 390812 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.8616. Min Act: -0.1700

Data Index: 1077594 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.7991. Min Act: -0.1700

Data Index: 264657 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.7054. Min Act: -0.1700

Data Index: 18220 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.7679. Min Act: -0.1700

Data Index: 962955 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.7679. Min Act: -0.1700

Data Index: 1112743 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.7679. Min Act: -0.1700

Data Index: 971089 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.7991. Min Act: -0.1700

Data Index: 356935 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.7366. Min Act: -0.1700

Data Index: 563658 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.7366. Min Act: -0.1700

Data Index: 415114 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.7366. Min Act: -0.1700

Data Index: 1313707 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.7679. Min Act: -0.1700

Data Index: 384899 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 5.0491. Min Range: -5.0491

Max Act: 4.7366. Min Act: -0.1700

Data Index: 233295 (C4 (Web Text))

Max Activating Token Index: 606