Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1045 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.5835. Min Act: -0.1700

Data Index: 1309322 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.4116. Min Act: -0.1700

Data Index: 494272 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.4584. Min Act: -0.1700

Data Index: 653649 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.4584. Min Act: -0.1700

Data Index: 230247 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.4116. Min Act: -0.1700

Data Index: 256497 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3647. Min Act: -0.1700

Data Index: 997074 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3491. Min Act: -0.1700

Data Index: 474101 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.3803. Min Act: -0.1700

Data Index: 390452 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.2397. Min Act: -0.1700

Data Index: 141051 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.2240. Min Act: -0.1696

Data Index: 890553 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.2084. Min Act: -0.1699

Data Index: 349536 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.2084. Min Act: -0.1700

Data Index: 1123045 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.2240. Min Act: -0.1700

Data Index: 1154032 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.1928. Min Act: -0.1700

Data Index: 384643 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.1772. Min Act: -0.1700

Data Index: 17483 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.1928. Min Act: -0.1700

Data Index: 394956 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.1615. Min Act: -0.1700

Data Index: 492233 (C4 (Web Text))

Max Activating Token Index: 814

Text #17

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.1928. Min Act: -0.1700

Data Index: 1250127 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.1303. Min Act: -0.1700

Data Index: 272119 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 4.5835. Min Range: -4.5835

Max Act: 4.1459. Min Act: -0.1700

Data Index: 1497841 (Python Code)

Max Activating Token Index: 37