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

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

Neuron 943 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: 5.4131. Min Range: -5.4131

Max Act: 5.3819. Min Act: -0.1700

Data Index: 1159197 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.4131. Min Act: -0.1700

Data Index: 188244 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.3506. Min Act: -0.1700

Data Index: 164726 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.3194. Min Act: -0.1700

Data Index: 707513 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.3194. Min Act: -0.1700

Data Index: 1088472 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.2569. Min Act: -0.1700

Data Index: 640670 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.2256. Min Act: -0.1700

Data Index: 116009 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.3819. Min Act: -0.1700

Data Index: 1128220 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.3194. Min Act: -0.1700

Data Index: 419352 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.2256. Min Act: -0.1700

Data Index: 347816 (C4 (Web Text))

Max Activating Token Index: 71

Text #10

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.2569. Min Act: -0.1700

Data Index: 1008720 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.2569. Min Act: -0.1700

Data Index: 385618 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.2256. Min Act: -0.1700

Data Index: 476536 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.1944. Min Act: -0.1700

Data Index: 261883 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.2256. Min Act: -0.1700

Data Index: 150208 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.3194. Min Act: -0.1700

Data Index: 594874 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.1944. Min Act: -0.1700

Data Index: 216109 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.1631. Min Act: -0.1700

Data Index: 1155242 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.1631. Min Act: -0.1700

Data Index: 1283587 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 5.4131. Min Range: -5.4131

Max Act: 5.0694. Min Act: -0.1700

Data Index: 458607 (C4 (Web Text))

Max Activating Token Index: 160