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

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

Neuron 1498 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: 5.1487. Min Range: -5.1487

Max Act: 5.1487. Min Act: -0.1700

Data Index: 361885 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.9612. Min Act: -0.1700

Data Index: 18826 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.9299. Min Act: -0.1700

Data Index: 563949 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.9924. Min Act: -0.1700

Data Index: 562891 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.8049. Min Act: -0.1700

Data Index: 715916 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.8049. Min Act: -0.1700

Data Index: 1008725 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.7424. Min Act: -0.1700

Data Index: 124893 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.6799. Min Act: -0.1700

Data Index: 982384 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.6799. Min Act: -0.1700

Data Index: 624738 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.6174. Min Act: -0.1700

Data Index: 1354475 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.6330. Min Act: -0.1700

Data Index: 546592 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.5862. Min Act: -0.1700

Data Index: 843764 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.5862. Min Act: -0.1695

Data Index: 1321093 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.5393. Min Act: -0.1700

Data Index: 1072129 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.6487. Min Act: -0.1700

Data Index: 1312560 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.5705. Min Act: -0.1700

Data Index: 707195 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.5862. Min Act: -0.1700

Data Index: 440388 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.5549. Min Act: -0.1700

Data Index: 932313 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.5237. Min Act: -0.1700

Data Index: 741522 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 5.1487. Min Range: -5.1487

Max Act: 4.5549. Min Act: -0.1700

Data Index: 973108 (C4 (Web Text))

Max Activating Token Index: 436