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

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

Neuron 1383 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.2131. Min Act: -0.1700

Data Index: 1343867 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.1344. Min Act: -0.1700

Data Index: 975232 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.1186. Min Act: -0.1700

Data Index: 317353 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.1186. Min Act: -0.1700

Data Index: 1232701 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.1344. Min Act: -0.1700

Data Index: 673876 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.0871. Min Act: -0.1700

Data Index: 618777 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.1028. Min Act: -0.1700

Data Index: 1018921 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.0713. Min Act: -0.1700

Data Index: 1019581 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.0713. Min Act: -0.1700

Data Index: 602714 (C4 (Web Text))

Max Activating Token Index: 472

Text #9

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.0555. Min Act: -0.1700

Data Index: 231683 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.0555. Min Act: -0.1700

Data Index: 1152055 (C4 (Web Text))

Max Activating Token Index: 366

Text #11

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.0397. Min Act: -0.1700

Data Index: 409434 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.0555. Min Act: -0.1700

Data Index: 599728 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.0239. Min Act: -0.1700

Data Index: 573504 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.0239. Min Act: -0.1700

Data Index: 1282139 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.0239. Min Act: -0.1700

Data Index: 1271417 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.0239. Min Act: -0.1700

Data Index: 73241 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 3.2131. Min Range: -3.2131

Max Act: 3.0239. Min Act: -0.1700

Data Index: 1020831 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.9923. Min Act: -0.1700

Data Index: 27567 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 3.2131. Min Range: -3.2131

Max Act: 2.9923. Min Act: -0.1700

Data Index: 99887 (C4 (Web Text))

Max Activating Token Index: 639