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

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

Neuron 1604 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: 3.5319. Min Range: -3.5319

Max Act: 3.5319. Min Act: -0.1700

Data Index: 922056 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.5006. Min Act: -0.1700

Data Index: 1197862 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.5006. Min Act: -0.1700

Data Index: 70122 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4693. Min Act: -0.1700

Data Index: 1275045 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4693. Min Act: -0.1700

Data Index: 409084 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4693. Min Act: -0.1700

Data Index: 284057 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4693. Min Act: -0.1700

Data Index: 872876 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4693. Min Act: -0.1700

Data Index: 868538 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4379. Min Act: -0.1700

Data Index: 276373 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4693. Min Act: -0.1700

Data Index: 1166973 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4066. Min Act: -0.1700

Data Index: 811332 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4066. Min Act: -0.1700

Data Index: 552936 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4066. Min Act: -0.1700

Data Index: 270226 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4379. Min Act: -0.1700

Data Index: 546470 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4693. Min Act: -0.1700

Data Index: 1116185 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4379. Min Act: -0.1700

Data Index: 1084604 (C4 (Web Text))

Max Activating Token Index: 690

Text #16

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4379. Min Act: -0.1700

Data Index: 546010 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4379. Min Act: -0.1700

Data Index: 906184 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4693. Min Act: -0.1700

Data Index: 110737 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 3.5319. Min Range: -3.5319

Max Act: 3.4379. Min Act: -0.1700

Data Index: 485386 (C4 (Web Text))

Max Activating Token Index: 161