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

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

Neuron 1776 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1030. Min Range: -3.1030

Max Act: 3.1030. Min Act: -0.1700

Data Index: 165694 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 3.1030. Min Range: -3.1030

Max Act: 3.0872. Min Act: -0.1700

Data Index: 31819 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 3.1030. Min Range: -3.1030

Max Act: 3.0399. Min Act: -0.1700

Data Index: 367154 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 3.1030. Min Range: -3.1030

Max Act: 3.0399. Min Act: -0.1700

Data Index: 949403 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 3.1030. Min Range: -3.1030

Max Act: 3.0241. Min Act: -0.1700

Data Index: 837894 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 3.1030. Min Range: -3.1030

Max Act: 3.0083. Min Act: -0.1700

Data Index: 883931 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 3.1030. Min Range: -3.1030

Max Act: 3.0241. Min Act: -0.1700

Data Index: 599349 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 3.1030. Min Range: -3.1030

Max Act: 3.0083. Min Act: -0.1700

Data Index: 1207632 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 3.1030. Min Range: -3.1030

Max Act: 2.9767. Min Act: -0.1700

Data Index: 984844 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 3.1030. Min Range: -3.1030

Max Act: 3.0083. Min Act: -0.1700

Data Index: 261870 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 3.1030. Min Range: -3.1030

Max Act: 2.9925. Min Act: -0.1700

Data Index: 748438 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 3.1030. Min Range: -3.1030

Max Act: 2.9767. Min Act: -0.1700

Data Index: 1034257 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 3.1030. Min Range: -3.1030

Max Act: 2.9925. Min Act: -0.1700

Data Index: 303962 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 3.1030. Min Range: -3.1030

Max Act: 2.9925. Min Act: -0.1700

Data Index: 648316 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 3.1030. Min Range: -3.1030

Max Act: 2.9925. Min Act: -0.1700

Data Index: 983873 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 3.1030. Min Range: -3.1030

Max Act: 2.9925. Min Act: -0.1700

Data Index: 721465 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 3.1030. Min Range: -3.1030

Max Act: 2.9767. Min Act: -0.1700

Data Index: 261106 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 3.1030. Min Range: -3.1030

Max Act: 2.9767. Min Act: -0.1700

Data Index: 40286 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 3.1030. Min Range: -3.1030

Max Act: 2.9767. Min Act: -0.1700

Data Index: 177303 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 3.1030. Min Range: -3.1030

Max Act: 2.9608. Min Act: -0.1700

Data Index: 719118 (C4 (Web Text))

Max Activating Token Index: 653