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

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

Neuron 1907 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: 3.1025. Min Range: -3.1025

Max Act: 3.1025. Min Act: -0.1700

Data Index: 577363 (C4 (Web Text))

Max Activating Token Index: 510

Text #1

Max Range: 3.1025. Min Range: -3.1025

Max Act: 3.0710. Min Act: -0.1700

Data Index: 522315 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.9604. Min Act: -0.1700

Data Index: 1005518 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.9445. Min Act: -0.1700

Data Index: 117598 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.9445. Min Act: -0.1700

Data Index: 1253586 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.9445. Min Act: -0.1700

Data Index: 1309275 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.9287. Min Act: -0.1700

Data Index: 607567 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.9128. Min Act: -0.1700

Data Index: 9677 (C4 (Web Text))

Max Activating Token Index: 498

Text #8

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.8970. Min Act: -0.1700

Data Index: 541150 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.8970. Min Act: -0.1700

Data Index: 1000382 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.9128. Min Act: -0.1700

Data Index: 1094060 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.8970. Min Act: -0.1700

Data Index: 84945 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.8652. Min Act: -0.1700

Data Index: 955914 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.8970. Min Act: -0.1700

Data Index: 538787 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.8811. Min Act: -0.1700

Data Index: 923383 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.8652. Min Act: -0.1700

Data Index: 276825 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.8652. Min Act: -0.1700

Data Index: 760059 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.8652. Min Act: -0.1700

Data Index: 1317931 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.8493. Min Act: -0.1700

Data Index: 203128 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 3.1025. Min Range: -3.1025

Max Act: 2.8652. Min Act: -0.1700

Data Index: 877079 (C4 (Web Text))

Max Activating Token Index: 128