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

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

Neuron 1985 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.4019. Min Act: -0.1700

Data Index: 248876 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.4019. Min Act: -0.1700

Data Index: 709568 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.3082. Min Act: -0.1700

Data Index: 1318444 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.3082. Min Act: -0.1700

Data Index: 812106 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.3082. Min Act: -0.1700

Data Index: 883456 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.2769. Min Act: -0.1700

Data Index: 106617 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.3082. Min Act: -0.1700

Data Index: 288262 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.2769. Min Act: -0.1700

Data Index: 1007063 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.2769. Min Act: -0.1700

Data Index: 137968 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.2457. Min Act: -0.1700

Data Index: 365746 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.2144. Min Act: -0.1700

Data Index: 456825 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.2457. Min Act: -0.1700

Data Index: 82266 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.2457. Min Act: -0.1700

Data Index: 160749 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.2457. Min Act: -0.1700

Data Index: 670337 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.2144. Min Act: -0.1700

Data Index: 727197 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.2457. Min Act: -0.1700

Data Index: 141739 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.2144. Min Act: -0.1700

Data Index: 410714 (C4 (Web Text))

Max Activating Token Index: 44

Text #17

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.2457. Min Act: -0.1700

Data Index: 749206 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.2144. Min Act: -0.1700

Data Index: 109707 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 4.4019. Min Range: -4.4019

Max Act: 4.2144. Min Act: -0.1700

Data Index: 807575 (C4 (Web Text))

Max Activating Token Index: 136