Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 353 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.7078. Min Act: -0.1700

Data Index: 892945 (C4 (Web Text))

Max Activating Token Index: 231

Text #1

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5825. Min Act: -0.1700

Data Index: 424345 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5825. Min Act: -0.1700

Data Index: 494560 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.4885. Min Act: -0.1700

Data Index: 464654 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5199. Min Act: -0.1700

Data Index: 824366 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5512. Min Act: -0.1700

Data Index: 1289445 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5042. Min Act: -0.1700

Data Index: 603044 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5512. Min Act: -0.1700

Data Index: 336377 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5042. Min Act: -0.1700

Data Index: 612356 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.4885. Min Act: -0.1700

Data Index: 1351602 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5199. Min Act: -0.1700

Data Index: 42655 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.4729. Min Act: -0.1700

Data Index: 1345373 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.5042. Min Act: -0.1700

Data Index: 927528 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.4729. Min Act: -0.1700

Data Index: 357008 (C4 (Web Text))

Max Activating Token Index: 451

Text #14

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.4729. Min Act: -0.1700

Data Index: 1112463 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.4572. Min Act: -0.1700

Data Index: 334004 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.4572. Min Act: -0.1700

Data Index: 354142 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.4415. Min Act: -0.1700

Data Index: 959694 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.4415. Min Act: -0.1700

Data Index: 383428 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 3.7078. Min Range: -3.7078

Max Act: 3.4572. Min Act: -0.1700

Data Index: 281940 (C4 (Web Text))

Max Activating Token Index: 942