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

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

Neuron 501 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0674. Min Act: -0.1700

Data Index: 812231 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0516. Min Act: -0.1700

Data Index: 618669 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0831. Min Act: -0.1700

Data Index: 82685 (C4 (Web Text))

Max Activating Token Index: 480

Text #3

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0674. Min Act: -0.1700

Data Index: 27628 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0200. Min Act: -0.1700

Data Index: 169211 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0674. Min Act: -0.1700

Data Index: 522549 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0674. Min Act: -0.1700

Data Index: 1351094 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0989. Min Act: -0.1700

Data Index: 451963 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0674. Min Act: -0.1700

Data Index: 1355153 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0358. Min Act: -0.1700

Data Index: 1356597 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0042. Min Act: -0.1700

Data Index: 27746 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0358. Min Act: -0.1700

Data Index: 858395 (C4 (Web Text))

Max Activating Token Index: 175

Text #12

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0042. Min Act: -0.1700

Data Index: 663225 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0358. Min Act: -0.1700

Data Index: 1345400 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0042. Min Act: -0.1700

Data Index: 41314 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9884. Min Act: -0.1700

Data Index: 939042 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9884. Min Act: -0.1700

Data Index: 856185 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 3.0989. Min Range: -3.0989

Max Act: 3.0042. Min Act: -0.1700

Data Index: 528093 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9567. Min Act: -0.1700

Data Index: 390430 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 3.0989. Min Range: -3.0989

Max Act: 2.9884. Min Act: -0.1700

Data Index: 849836 (C4 (Web Text))

Max Activating Token Index: 166