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

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

Neuron 260 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.7959. Min Act: -0.1700

Data Index: 1224911 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.5459. Min Act: -0.1700

Data Index: 1115282 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.4521. Min Act: -0.1700

Data Index: 49648 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.4521. Min Act: -0.1700

Data Index: 728517 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.3584. Min Act: -0.1700

Data Index: 1310586 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.3584. Min Act: -0.1700

Data Index: 577030 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.3584. Min Act: -0.1700

Data Index: 650069 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.3896. Min Act: -0.1700

Data Index: 373059 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.3271. Min Act: -0.1700

Data Index: 188474 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.3271. Min Act: -0.1700

Data Index: 470612 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.3271. Min Act: -0.1700

Data Index: 1021827 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.3271. Min Act: -0.1700

Data Index: 809157 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.3271. Min Act: -0.1700

Data Index: 1271010 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.2959. Min Act: -0.1700

Data Index: 1039758 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.2334. Min Act: -0.1700

Data Index: 8824 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.2646. Min Act: -0.1700

Data Index: 7448 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.2334. Min Act: -0.1700

Data Index: 286152 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.2021. Min Act: -0.1700

Data Index: 619793 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.2021. Min Act: -0.1700

Data Index: 296767 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 5.7959. Min Range: -5.7959

Max Act: 5.2334. Min Act: -0.1700

Data Index: 154950 (C4 (Web Text))

Max Activating Token Index: 938