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

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

Neuron 965 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.2548. Min Act: -0.1700

Data Index: 647735 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.2391. Min Act: -0.1700

Data Index: 86628 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.2077. Min Act: -0.1700

Data Index: 385360 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.2077. Min Act: -0.1700

Data Index: 469922 (C4 (Web Text))

Max Activating Token Index: 79

Text #4

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.2234. Min Act: -0.1700

Data Index: 38528 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.1605. Min Act: -0.1700

Data Index: 1335841 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.1762. Min Act: -0.1700

Data Index: 540260 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.0974. Min Act: -0.1700

Data Index: 439693 (C4 (Web Text))

Max Activating Token Index: 756

Text #8

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.1447. Min Act: -0.1700

Data Index: 911597 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.0817. Min Act: -0.1700

Data Index: 635112 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.1290. Min Act: -0.1700

Data Index: 1058582 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.1132. Min Act: -0.1700

Data Index: 1057419 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.1132. Min Act: -0.1700

Data Index: 180142 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.1132. Min Act: -0.1700

Data Index: 469894 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.0817. Min Act: -0.1700

Data Index: 656935 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.0659. Min Act: -0.1700

Data Index: 278991 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.0659. Min Act: -0.1700

Data Index: 726577 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.0343. Min Act: -0.1700

Data Index: 818455 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.0501. Min Act: -0.1700

Data Index: 533698 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 3.2548. Min Range: -3.2548

Max Act: 3.1132. Min Act: -0.1700

Data Index: 122532 (C4 (Web Text))

Max Activating Token Index: 336