Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 268 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.6200. Min Act: -0.1700

Data Index: 261001 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.5730. Min Act: -0.1700

Data Index: 317339 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.5574. Min Act: -0.1700

Data Index: 924479 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.5260. Min Act: -0.1700

Data Index: 1044150 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.5104. Min Act: -0.1700

Data Index: 897829 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.5260. Min Act: -0.1700

Data Index: 497886 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.5104. Min Act: -0.1700

Data Index: 381470 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.5260. Min Act: -0.1700

Data Index: 500253 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.4947. Min Act: -0.1700

Data Index: 500031 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.5104. Min Act: -0.1700

Data Index: 700561 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.5260. Min Act: -0.1700

Data Index: 1114569 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.5104. Min Act: -0.1700

Data Index: 120649 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.5104. Min Act: -0.1700

Data Index: 45177 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.5104. Min Act: -0.1700

Data Index: 12143 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.4947. Min Act: -0.1700

Data Index: 799118 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.4790. Min Act: -0.1700

Data Index: 308568 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.4790. Min Act: -0.1700

Data Index: 265276 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.4947. Min Act: -0.1700

Data Index: 916896 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.4947. Min Act: -0.1700

Data Index: 575155 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.4947. Min Act: -0.1700

Data Index: 239887 (C4 (Web Text))

Max Activating Token Index: 359