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

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

Neuron 1268 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: 3.4632. Min Range: -3.4632

Max Act: 3.4632. Min Act: -0.1700

Data Index: 28686 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.4005. Min Act: -0.1700

Data Index: 514821 (C4 (Web Text))

Max Activating Token Index: 305

Text #2

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.3691. Min Act: -0.1700

Data Index: 651107 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.3534. Min Act: -0.1700

Data Index: 275090 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.2906. Min Act: -0.1700

Data Index: 448506 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.3063. Min Act: -0.1700

Data Index: 367608 (C4 (Web Text))

Max Activating Token Index: 682

Text #6

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.3063. Min Act: -0.1700

Data Index: 1032687 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.2592. Min Act: -0.1700

Data Index: 302468 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.2435. Min Act: -0.1700

Data Index: 1273844 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.2592. Min Act: -0.1700

Data Index: 425624 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.2435. Min Act: -0.1700

Data Index: 1050961 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.2277. Min Act: -0.1700

Data Index: 1096498 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.1963. Min Act: -0.1700

Data Index: 202060 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.2435. Min Act: -0.1700

Data Index: 1341032 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.1963. Min Act: -0.1700

Data Index: 1160303 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.1963. Min Act: -0.1700

Data Index: 546535 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.1648. Min Act: -0.1700

Data Index: 573036 (C4 (Web Text))

Max Activating Token Index: 931

Text #17

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.1648. Min Act: -0.1700

Data Index: 698744 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.1648. Min Act: -0.1700

Data Index: 20805 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 3.4632. Min Range: -3.4632

Max Act: 3.1333. Min Act: -0.1700

Data Index: 536310 (C4 (Web Text))

Max Activating Token Index: 244