Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2923 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.3642. Min Range: -4.3642

Max Act: 4.3642. Min Act: -0.1700

Data Index: 6885024 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 4.3642. Min Range: -4.3642

Max Act: 4.0146. Min Act: -0.1700

Data Index: 6835093 (Open Web Text)

Max Activating Token Index: 208

Text #2

Max Range: 4.3642. Min Range: -4.3642

Max Act: 4.0089. Min Act: -0.1700

Data Index: 2642343 (Open Web Text)

Max Activating Token Index: 692

Text #3

Max Range: 4.3642. Min Range: -4.3642

Max Act: 4.0251. Min Act: -0.1700

Data Index: 6213679 (Open Web Text)

Max Activating Token Index: 809

Text #4

Max Range: 4.3642. Min Range: -4.3642

Max Act: 3.9579. Min Act: -0.1700

Data Index: 7460030 (Open Web Text)

Max Activating Token Index: 178

Text #5

Max Range: 4.3642. Min Range: -4.3642

Max Act: 3.8926. Min Act: -0.1700

Data Index: 2993263 (Open Web Text)

Max Activating Token Index: 635

Text #6

Max Range: 4.3642. Min Range: -4.3642

Max Act: 3.8467. Min Act: -0.1700

Data Index: 4842453 (Open Web Text)

Max Activating Token Index: 248

Text #7

Max Range: 4.3642. Min Range: -4.3642

Max Act: 3.8622. Min Act: -0.1700

Data Index: 7246234 (Open Web Text)

Max Activating Token Index: 885

Text #8

Max Range: 4.3642. Min Range: -4.3642

Max Act: 3.8343. Min Act: -0.1700

Data Index: 7448391 (Open Web Text)

Max Activating Token Index: 66

Text #9

Max Range: 4.3642. Min Range: -4.3642

Max Act: 3.7606. Min Act: -0.1700

Data Index: 6835092 (Open Web Text)

Max Activating Token Index: 240

Text #10

Max Range: 4.3642. Min Range: -4.3642

Max Act: 3.7900. Min Act: -0.1700

Data Index: 8635764 (Open Web Text)

Max Activating Token Index: 715

Text #11

Max Range: 4.3642. Min Range: -4.3642

Max Act: 3.7765. Min Act: -0.1700

Data Index: 4200209 (Open Web Text)

Max Activating Token Index: 735

Text #12

Max Range: 4.3642. Min Range: -4.3642

Max Act: 3.7735. Min Act: -0.1700

Data Index: 2994605 (Open Web Text)

Max Activating Token Index: 937

Text #13

Max Range: 4.3642. Min Range: -4.3642

Max Act: 3.7850. Min Act: -0.1700

Data Index: 4686 (Open Web Text)

Max Activating Token Index: 246

Text #14

Max Range: 4.3642. Min Range: -4.3642

Max Act: 3.7028. Min Act: -0.1700

Data Index: 7824218 (Open Web Text)

Max Activating Token Index: 774

Text #15

Max Range: 4.3642. Min Range: -4.3642

Max Act: 3.7312. Min Act: -0.1700

Data Index: 6835094 (Open Web Text)

Max Activating Token Index: 339

Text #16

Max Range: 4.3642. Min Range: -4.3642

Max Act: 3.7104. Min Act: -0.1700

Data Index: 6451311 (Open Web Text)

Max Activating Token Index: 573

Text #17

Max Range: 4.3642. Min Range: -4.3642

Max Act: 3.7437. Min Act: -0.1700

Data Index: 497396 (Open Web Text)

Max Activating Token Index: 396

Text #18

Max Range: 4.3642. Min Range: -4.3642

Max Act: 3.7137. Min Act: -0.1700

Data Index: 3509845 (Open Web Text)

Max Activating Token Index: 30

Text #19

Max Range: 4.3642. Min Range: -4.3642

Max Act: 3.6841. Min Act: -0.1700

Data Index: 3335389 (Open Web Text)

Max Activating Token Index: 781