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

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

Neuron 174 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: 8.9359. Min Range: -8.9359

Max Act: 8.9359. Min Act: -0.1700

Data Index: 162801 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.5609. Min Act: -0.1700

Data Index: 470320 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.5609. Min Act: -0.1700

Data Index: 200343 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.6234. Min Act: -0.1700

Data Index: 966750 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.6859. Min Act: -0.1700

Data Index: 157700 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.4984. Min Act: -0.1700

Data Index: 365331 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.5609. Min Act: -0.1700

Data Index: 601818 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.4984. Min Act: -0.1700

Data Index: 760296 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.5609. Min Act: -0.1700

Data Index: 582629 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.4984. Min Act: -0.1700

Data Index: 584751 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.1234. Min Act: -0.1700

Data Index: 555903 (C4 (Web Text))

Max Activating Token Index: 410

Text #11

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.4984. Min Act: -0.1700

Data Index: 281912 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.3734. Min Act: -0.1700

Data Index: 757713 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.1859. Min Act: -0.1699

Data Index: 1104748 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.4984. Min Act: -0.1700

Data Index: 751363 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.4984. Min Act: -0.1700

Data Index: 1208064 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.3734. Min Act: -0.1700

Data Index: 385051 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.2484. Min Act: -0.1700

Data Index: 334444 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.3109. Min Act: -0.1699

Data Index: 771598 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 8.9359. Min Range: -8.9359

Max Act: 8.2484. Min Act: -0.1700

Data Index: 25049 (C4 (Web Text))

Max Activating Token Index: 850