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

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

Neuron 1276 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: 3.4223. Min Range: -3.4223

Max Act: 3.4223. Min Act: -0.1700

Data Index: 1206187 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.3438. Min Act: -0.1700

Data Index: 1092666 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.3438. Min Act: -0.1700

Data Index: 1317171 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.3281. Min Act: -0.1700

Data Index: 285922 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.3281. Min Act: -0.1700

Data Index: 16251 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.3124. Min Act: -0.1700

Data Index: 526166 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.2810. Min Act: -0.1700

Data Index: 579339 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.2653. Min Act: -0.1700

Data Index: 148919 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.2967. Min Act: -0.1700

Data Index: 328801 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.2181. Min Act: -0.1700

Data Index: 208486 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.2653. Min Act: -0.1700

Data Index: 36895 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.2653. Min Act: -0.1700

Data Index: 1154404 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.2810. Min Act: -0.1700

Data Index: 523606 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.2339. Min Act: -0.1700

Data Index: 605570 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.2810. Min Act: -0.1700

Data Index: 679375 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.2810. Min Act: -0.1700

Data Index: 254879 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.2653. Min Act: -0.1700

Data Index: 1338979 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.2496. Min Act: -0.1700

Data Index: 769345 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.2653. Min Act: -0.1700

Data Index: 233499 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 3.4223. Min Range: -3.4223

Max Act: 3.2653. Min Act: -0.1700

Data Index: 62141 (C4 (Web Text))

Max Activating Token Index: 350