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

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

Neuron 162 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.6718. Min Act: -0.1700

Data Index: 998037 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.4843. Min Act: -0.1700

Data Index: 760553 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.3905. Min Act: -0.1700

Data Index: 49395 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.5780. Min Act: -0.1700

Data Index: 1125830 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.4218. Min Act: -0.1700

Data Index: 517470 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.4843. Min Act: -0.1700

Data Index: 860928 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.3593. Min Act: -0.1700

Data Index: 460111 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.3280. Min Act: -0.1700

Data Index: 867057 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.3593. Min Act: -0.1700

Data Index: 392390 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.2968. Min Act: -0.1700

Data Index: 471096 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.3280. Min Act: -0.1700

Data Index: 665164 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.2343. Min Act: -0.1700

Data Index: 1286846 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.2343. Min Act: -0.1700

Data Index: 1046122 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.1718. Min Act: -0.1700

Data Index: 413331 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.2655. Min Act: -0.1700

Data Index: 1289843 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.2030. Min Act: -0.1700

Data Index: 670918 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.1718. Min Act: -0.1700

Data Index: 96282 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.2030. Min Act: -0.1700

Data Index: 998438 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.1093. Min Act: -0.1700

Data Index: 1129131 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 5.6718. Min Range: -5.6718

Max Act: 5.0780. Min Act: -0.1700

Data Index: 236916 (C4 (Web Text))

Max Activating Token Index: 743