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

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

Neuron 1546 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.9841. Min Act: -0.1700

Data Index: 596514 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.9216. Min Act: -0.1700

Data Index: 712948 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.9216. Min Act: -0.1700

Data Index: 579858 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.8903. Min Act: -0.1700

Data Index: 617525 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.8903. Min Act: -0.1700

Data Index: 175494 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.8903. Min Act: -0.1700

Data Index: 260049 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.8590. Min Act: -0.1700

Data Index: 1210625 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.7965. Min Act: -0.1700

Data Index: 75914 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.8278. Min Act: -0.1700

Data Index: 537917 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.8590. Min Act: -0.1700

Data Index: 372849 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.8278. Min Act: -0.1700

Data Index: 823125 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.8278. Min Act: -0.1700

Data Index: 309201 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.7965. Min Act: -0.1700

Data Index: 293471 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.7965. Min Act: -0.1700

Data Index: 1344534 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.7652. Min Act: -0.1700

Data Index: 139295 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.7965. Min Act: -0.1700

Data Index: 423672 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.7965. Min Act: -0.1700

Data Index: 1106134 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.7652. Min Act: -0.1700

Data Index: 1077652 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.7652. Min Act: -0.1700

Data Index: 196695 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 3.9841. Min Range: -3.9841

Max Act: 3.7652. Min Act: -0.1700

Data Index: 747673 (C4 (Web Text))

Max Activating Token Index: 983