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

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

Neuron 1912 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: 5.4941. Min Range: -5.4941

Max Act: 5.4628. Min Act: -0.1700

Data Index: 908678 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.4941. Min Act: -0.1700

Data Index: 971751 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.2753. Min Act: -0.1700

Data Index: 587411 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.3066. Min Act: -0.1700

Data Index: 127091 (C4 (Web Text))

Max Activating Token Index: 509

Text #4

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.2753. Min Act: -0.1700

Data Index: 826163 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.3066. Min Act: -0.1700

Data Index: 252143 (C4 (Web Text))

Max Activating Token Index: 772

Text #6

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.3066. Min Act: -0.1700

Data Index: 277672 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.3066. Min Act: -0.1700

Data Index: 234471 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.2441. Min Act: -0.1700

Data Index: 587587 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.1191. Min Act: -0.1700

Data Index: 1212390 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.0878. Min Act: -0.1700

Data Index: 1016297 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.1816. Min Act: -0.1700

Data Index: 802005 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.2128. Min Act: -0.1700

Data Index: 259988 (C4 (Web Text))

Max Activating Token Index: 425

Text #13

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.1816. Min Act: -0.1700

Data Index: 483386 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.0878. Min Act: -0.1700

Data Index: 529446 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.0566. Min Act: -0.1700

Data Index: 685044 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.0878. Min Act: -0.1700

Data Index: 1080 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.0566. Min Act: -0.1700

Data Index: 1134787 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.0878. Min Act: -0.1700

Data Index: 948082 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 5.4941. Min Range: -5.4941

Max Act: 5.0566. Min Act: -0.1700

Data Index: 795970 (C4 (Web Text))

Max Activating Token Index: 620