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

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

Neuron 821 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: 3.2603. Min Range: -3.2603

Max Act: 3.2603. Min Act: -0.1700

Data Index: 899214 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.2132. Min Act: -0.1700

Data Index: 952125 (C4 (Web Text))

Max Activating Token Index: 242

Text #2

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.1029. Min Act: -0.1700

Data Index: 1306800 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0556. Min Act: -0.1700

Data Index: 925086 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0398. Min Act: -0.1700

Data Index: 483391 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0556. Min Act: -0.1700

Data Index: 76947 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0240. Min Act: -0.1700

Data Index: 452189 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0398. Min Act: -0.1700

Data Index: 509553 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0398. Min Act: -0.1700

Data Index: 106353 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0240. Min Act: -0.1700

Data Index: 1231535 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 3.2603. Min Range: -3.2603

Max Act: 2.9924. Min Act: -0.1700

Data Index: 397938 (C4 (Web Text))

Max Activating Token Index: 503

Text #11

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0082. Min Act: -0.1700

Data Index: 812769 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0082. Min Act: -0.1700

Data Index: 369917 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 3.2603. Min Range: -3.2603

Max Act: 3.0082. Min Act: -0.1700

Data Index: 157379 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 3.2603. Min Range: -3.2603

Max Act: 2.9924. Min Act: -0.1700

Data Index: 677066 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 3.2603. Min Range: -3.2603

Max Act: 2.9766. Min Act: -0.1700

Data Index: 896896 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 3.2603. Min Range: -3.2603

Max Act: 2.9924. Min Act: -0.1700

Data Index: 685056 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 3.2603. Min Range: -3.2603

Max Act: 2.9924. Min Act: -0.1700

Data Index: 753730 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 3.2603. Min Range: -3.2603

Max Act: 2.9924. Min Act: -0.1700

Data Index: 185588 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 3.2603. Min Range: -3.2603

Max Act: 2.9924. Min Act: -0.1700

Data Index: 937759 (C4 (Web Text))

Max Activating Token Index: 889