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

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

Neuron 436 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0673. Min Range: -4.0673

Max Act: 4.0673. Min Act: -0.1700

Data Index: 35240 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.9110. Min Act: -0.1700

Data Index: 63457 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.8641. Min Act: -0.1700

Data Index: 440988 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.8484. Min Act: -0.1700

Data Index: 830436 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.8171. Min Act: -0.1700

Data Index: 509665 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.8171. Min Act: -0.1700

Data Index: 571723 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.8015. Min Act: -0.1700

Data Index: 385733 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.8484. Min Act: -0.1700

Data Index: 518735 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.8171. Min Act: -0.1700

Data Index: 455358 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.7702. Min Act: -0.1700

Data Index: 599279 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.7702. Min Act: -0.1700

Data Index: 251897 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.7233. Min Act: -0.1700

Data Index: 899921 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.7076. Min Act: -0.1700

Data Index: 216020 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.7233. Min Act: -0.1700

Data Index: 163879 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.6920. Min Act: -0.1700

Data Index: 494523 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.7233. Min Act: -0.1700

Data Index: 362632 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.7076. Min Act: -0.1700

Data Index: 107102 (C4 (Web Text))

Max Activating Token Index: 246

Text #17

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.7076. Min Act: -0.1700

Data Index: 471710 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.6763. Min Act: -0.1700

Data Index: 1344479 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 4.0673. Min Range: -4.0673

Max Act: 3.6920. Min Act: -0.1700

Data Index: 77802 (C4 (Web Text))

Max Activating Token Index: 689