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

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

Neuron 751 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: 5.1698. Min Range: -5.1698

Max Act: 5.1698. Min Act: -0.1700

Data Index: 1187470 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.1073. Min Act: -0.1700

Data Index: 1118879 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.1385. Min Act: -0.1700

Data Index: 949584 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.1385. Min Act: -0.1700

Data Index: 180417 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.1385. Min Act: -0.1700

Data Index: 1051139 (C4 (Web Text))

Max Activating Token Index: 75

Text #5

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.1073. Min Act: -0.1700

Data Index: 119164 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.1698. Min Act: -0.1700

Data Index: 601683 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.1385. Min Act: -0.1700

Data Index: 1000303 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.1385. Min Act: -0.1700

Data Index: 1180741 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.1073. Min Act: -0.1700

Data Index: 1355958 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.1073. Min Act: -0.1700

Data Index: 36421 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.1073. Min Act: -0.1700

Data Index: 416180 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.1385. Min Act: -0.1700

Data Index: 116484 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.0760. Min Act: -0.1700

Data Index: 510350 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.0760. Min Act: -0.1700

Data Index: 181559 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.0760. Min Act: -0.1700

Data Index: 385842 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.0760. Min Act: -0.1700

Data Index: 133942 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.0760. Min Act: -0.1700

Data Index: 63315 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.0135. Min Act: -0.1700

Data Index: 1163922 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 5.1698. Min Range: -5.1698

Max Act: 5.0448. Min Act: -0.1700

Data Index: 980932 (C4 (Web Text))

Max Activating Token Index: 57