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

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

Neuron 179 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: 5.2364. Min Range: -5.2364

Max Act: 5.2364. Min Act: -0.1700

Data Index: 188693 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 5.2364. Min Range: -5.2364

Max Act: 5.0801. Min Act: -0.1700

Data Index: 472286 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.9551. Min Act: -0.1700

Data Index: 400551 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.9864. Min Act: -0.1700

Data Index: 1021154 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.8614. Min Act: -0.1700

Data Index: 1303688 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.9239. Min Act: -0.1700

Data Index: 565454 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.8614. Min Act: -0.1700

Data Index: 1291657 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.7989. Min Act: -0.1700

Data Index: 138607 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.7989. Min Act: -0.1700

Data Index: 261660 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.7989. Min Act: -0.1700

Data Index: 750304 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.7676. Min Act: -0.1700

Data Index: 249422 (C4 (Web Text))

Max Activating Token Index: 981

Text #11

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.7051. Min Act: -0.1700

Data Index: 285612 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.7989. Min Act: -0.1700

Data Index: 194281 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.7051. Min Act: -0.1700

Data Index: 1113445 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.7051. Min Act: -0.1700

Data Index: 1138158 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.7051. Min Act: -0.1700

Data Index: 316397 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.6426. Min Act: -0.1700

Data Index: 693403 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.6739. Min Act: -0.1691

Data Index: 727704 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.7051. Min Act: -0.1700

Data Index: 848849 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 5.2364. Min Range: -5.2364

Max Act: 4.6426. Min Act: -0.1700

Data Index: 58641 (C4 (Web Text))

Max Activating Token Index: 593