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

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

Neuron 580 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: 5.1427. Min Range: -5.1427

Max Act: 5.1427. Min Act: -0.1700

Data Index: 604420 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 5.1427. Min Range: -5.1427

Max Act: 5.0802. Min Act: -0.1700

Data Index: 189107 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 5.1427. Min Range: -5.1427

Max Act: 5.0802. Min Act: -0.1700

Data Index: 1344737 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 5.1427. Min Range: -5.1427

Max Act: 5.0802. Min Act: -0.1700

Data Index: 1001164 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 5.1427. Min Range: -5.1427

Max Act: 4.9865. Min Act: -0.1700

Data Index: 1185853 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 5.1427. Min Range: -5.1427

Max Act: 4.9865. Min Act: -0.1700

Data Index: 801930 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 5.1427. Min Range: -5.1427

Max Act: 5.0490. Min Act: -0.1700

Data Index: 165801 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 5.1427. Min Range: -5.1427

Max Act: 5.0490. Min Act: -0.1700

Data Index: 954567 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 5.1427. Min Range: -5.1427

Max Act: 4.9552. Min Act: -0.1700

Data Index: 1298123 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 5.1427. Min Range: -5.1427

Max Act: 4.9865. Min Act: -0.1700

Data Index: 845987 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 5.1427. Min Range: -5.1427

Max Act: 4.9865. Min Act: -0.1700

Data Index: 253019 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 5.1427. Min Range: -5.1427

Max Act: 5.0177. Min Act: -0.1700

Data Index: 574840 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 5.1427. Min Range: -5.1427

Max Act: 4.9865. Min Act: -0.1700

Data Index: 123879 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 5.1427. Min Range: -5.1427

Max Act: 4.8927. Min Act: -0.1700

Data Index: 74172 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 5.1427. Min Range: -5.1427

Max Act: 4.9552. Min Act: -0.1700

Data Index: 1055918 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 5.1427. Min Range: -5.1427

Max Act: 4.9552. Min Act: -0.1700

Data Index: 462831 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 5.1427. Min Range: -5.1427

Max Act: 4.8615. Min Act: -0.1700

Data Index: 89231 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 5.1427. Min Range: -5.1427

Max Act: 4.9240. Min Act: -0.1700

Data Index: 799039 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 5.1427. Min Range: -5.1427

Max Act: 5.0177. Min Act: -0.1700

Data Index: 1035239 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 5.1427. Min Range: -5.1427

Max Act: 4.8927. Min Act: -0.1700

Data Index: 431385 (C4 (Web Text))

Max Activating Token Index: 365