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

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

Neuron 1102 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: 3.5134. Min Range: -3.5134

Max Act: 3.5134. Min Act: -0.1700

Data Index: 580553 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.4821. Min Act: -0.1700

Data Index: 956761 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.4821. Min Act: -0.1700

Data Index: 1152704 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.4507. Min Act: -0.1700

Data Index: 1266858 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.4821. Min Act: -0.1700

Data Index: 686577 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.4507. Min Act: -0.1700

Data Index: 1217271 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.4507. Min Act: -0.1700

Data Index: 214370 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.4351. Min Act: -0.1700

Data Index: 981156 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.4351. Min Act: -0.1700

Data Index: 267920 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.4351. Min Act: -0.1700

Data Index: 249843 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.4194. Min Act: -0.1700

Data Index: 439274 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.4194. Min Act: -0.1700

Data Index: 497245 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.3880. Min Act: -0.1700

Data Index: 584641 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.3880. Min Act: -0.1700

Data Index: 426849 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.3880. Min Act: -0.1700

Data Index: 1173775 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.3880. Min Act: -0.1700

Data Index: 363490 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.3880. Min Act: -0.1700

Data Index: 1202751 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.3880. Min Act: -0.1700

Data Index: 565076 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.3880. Min Act: -0.1700

Data Index: 1257714 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 3.5134. Min Range: -3.5134

Max Act: 3.3723. Min Act: -0.1700

Data Index: 962604 (C4 (Web Text))

Max Activating Token Index: 33