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

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

Neuron 1399 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: 7.1302. Min Range: -7.1302

Max Act: 7.1302. Min Act: -0.1700

Data Index: 529979 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 7.1302. Min Range: -7.1302

Max Act: 7.0052. Min Act: -0.1700

Data Index: 887737 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 7.1302. Min Range: -7.1302

Max Act: 7.0052. Min Act: -0.1700

Data Index: 1338882 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 7.1302. Min Range: -7.1302

Max Act: 7.0052. Min Act: -0.1700

Data Index: 1312330 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 7.1302. Min Range: -7.1302

Max Act: 7.0052. Min Act: -0.1700

Data Index: 594353 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 7.1302. Min Range: -7.1302

Max Act: 7.0052. Min Act: -0.1700

Data Index: 251224 (C4 (Web Text))

Max Activating Token Index: 827

Text #6

Max Range: 7.1302. Min Range: -7.1302

Max Act: 7.0052. Min Act: -0.1700

Data Index: 1023153 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 7.1302. Min Range: -7.1302

Max Act: 7.0052. Min Act: -0.1700

Data Index: 471450 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 7.1302. Min Range: -7.1302

Max Act: 7.0677. Min Act: -0.1700

Data Index: 457587 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 7.1302. Min Range: -7.1302

Max Act: 7.0052. Min Act: -0.1700

Data Index: 1292493 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 7.1302. Min Range: -7.1302

Max Act: 7.0052. Min Act: -0.1700

Data Index: 1275718 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 7.1302. Min Range: -7.1302

Max Act: 6.9427. Min Act: -0.1700

Data Index: 566344 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 7.1302. Min Range: -7.1302

Max Act: 6.8802. Min Act: -0.1700

Data Index: 606233 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 7.1302. Min Range: -7.1302

Max Act: 6.9427. Min Act: -0.1700

Data Index: 561907 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 7.1302. Min Range: -7.1302

Max Act: 7.0052. Min Act: -0.1700

Data Index: 783079 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 7.1302. Min Range: -7.1302

Max Act: 6.9427. Min Act: -0.1700

Data Index: 908224 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 7.1302. Min Range: -7.1302

Max Act: 6.9427. Min Act: -0.1700

Data Index: 273074 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 7.1302. Min Range: -7.1302

Max Act: 6.8177. Min Act: -0.1700

Data Index: 1184825 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 7.1302. Min Range: -7.1302

Max Act: 6.9427. Min Act: -0.1700

Data Index: 846466 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 7.1302. Min Range: -7.1302

Max Act: 6.8802. Min Act: -0.1700

Data Index: 695291 (C4 (Web Text))

Max Activating Token Index: 266