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

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

Neuron 1076 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: 3.5208. Min Range: -3.5208

Max Act: 3.4895. Min Act: -0.1700

Data Index: 515670 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.5208. Min Act: -0.1700

Data Index: 650677 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4895. Min Act: -0.1700

Data Index: 673299 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4738. Min Act: -0.1700

Data Index: 604290 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4738. Min Act: -0.1700

Data Index: 1072260 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4581. Min Act: -0.1700

Data Index: 7154 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4581. Min Act: -0.1700

Data Index: 468816 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4425. Min Act: -0.1700

Data Index: 1328781 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4111. Min Act: -0.1700

Data Index: 892013 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4111. Min Act: -0.1700

Data Index: 641514 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3954. Min Act: -0.1700

Data Index: 1129122 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.4111. Min Act: -0.1700

Data Index: 146449 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3954. Min Act: -0.1700

Data Index: 194663 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3797. Min Act: -0.1700

Data Index: 485763 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3640. Min Act: -0.1700

Data Index: 145678 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3797. Min Act: -0.1700

Data Index: 608029 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3954. Min Act: -0.1700

Data Index: 451073 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3797. Min Act: -0.1700

Data Index: 1355824 (C4 (Web Text))

Max Activating Token Index: 757

Text #18

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3483. Min Act: -0.1700

Data Index: 1269313 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 3.5208. Min Range: -3.5208

Max Act: 3.3327. Min Act: -0.1700

Data Index: 977149 (C4 (Web Text))

Max Activating Token Index: 625