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

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

Neuron 422 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.8808. Min Act: -0.1700

Data Index: 1216945 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.8182. Min Act: -0.1700

Data Index: 1356063 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.8182. Min Act: -0.1700

Data Index: 929179 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.8182. Min Act: -0.1700

Data Index: 1074162 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.7244. Min Act: -0.1700

Data Index: 1035206 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.7244. Min Act: -0.1700

Data Index: 808801 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.7557. Min Act: -0.1700

Data Index: 1030618 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.6618. Min Act: -0.1700

Data Index: 218027 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.6618. Min Act: -0.1700

Data Index: 852177 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.6618. Min Act: -0.1700

Data Index: 1085721 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.6305. Min Act: -0.1700

Data Index: 917500 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.6618. Min Act: -0.1700

Data Index: 547111 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.6305. Min Act: -0.1700

Data Index: 586532 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.6774. Min Act: -0.1700

Data Index: 162408 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.6305. Min Act: -0.1700

Data Index: 464276 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.6618. Min Act: -0.1700

Data Index: 310209 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.5992. Min Act: -0.1700

Data Index: 19717 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.5835. Min Act: -0.1700

Data Index: 608122 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.5992. Min Act: -0.1700

Data Index: 1192579 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 3.8808. Min Range: -3.8808

Max Act: 3.6305. Min Act: -0.1700

Data Index: 1245890 (C4 (Web Text))

Max Activating Token Index: 268