Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 506 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.6637. Min Act: -0.1700

Data Index: 1303371 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.4762. Min Act: -0.1700

Data Index: 386403 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.5387. Min Act: -0.1700

Data Index: 10669 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.4449. Min Act: -0.1700

Data Index: 326595 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.5074. Min Act: -0.1700

Data Index: 1228460 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.5074. Min Act: -0.1700

Data Index: 744288 (C4 (Web Text))

Max Activating Token Index: 334

Text #6

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.4762. Min Act: -0.1700

Data Index: 377869 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.3824. Min Act: -0.1700

Data Index: 332402 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.4137. Min Act: -0.1700

Data Index: 1172811 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.3824. Min Act: -0.1700

Data Index: 757038 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.3824. Min Act: -0.1700

Data Index: 368889 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.3824. Min Act: -0.1700

Data Index: 1347844 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.3824. Min Act: -0.1700

Data Index: 508830 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.3512. Min Act: -0.1700

Data Index: 15830 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.3512. Min Act: -0.1700

Data Index: 832327 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.3824. Min Act: -0.1700

Data Index: 540963 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.3824. Min Act: -0.1700

Data Index: 34600 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.3824. Min Act: -0.1700

Data Index: 453576 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.3199. Min Act: -0.1700

Data Index: 133161 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 5.6637. Min Range: -5.6637

Max Act: 5.3199. Min Act: -0.1700

Data Index: 29984 (C4 (Web Text))

Max Activating Token Index: 645