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

Dataset: Open Web Text

Neuron 688 in Layer 5

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: 6.3696. Min Range: -6.3696

Max Act: 6.3696. Min Act: -0.1700

Data Index: 3991286 (Open Web Text)

Max Activating Token Index: 388

Text #1

Max Range: 6.3696. Min Range: -6.3696

Max Act: 6.2537. Min Act: -0.1700

Data Index: 236727 (Open Web Text)

Max Activating Token Index: 390

Text #2

Max Range: 6.3696. Min Range: -6.3696

Max Act: 6.1300. Min Act: -0.1700

Data Index: 4447201 (Open Web Text)

Max Activating Token Index: 181

Text #3

Max Range: 6.3696. Min Range: -6.3696

Max Act: 6.0245. Min Act: -0.1700

Data Index: 1839384 (Open Web Text)

Max Activating Token Index: 93

Text #4

Max Range: 6.3696. Min Range: -6.3696

Max Act: 5.9017. Min Act: -0.1700

Data Index: 6540444 (Open Web Text)

Max Activating Token Index: 519

Text #5

Max Range: 6.3696. Min Range: -6.3696

Max Act: 5.9243. Min Act: -0.1700

Data Index: 3998711 (Open Web Text)

Max Activating Token Index: 541

Text #6

Max Range: 6.3696. Min Range: -6.3696

Max Act: 5.8200. Min Act: -0.1700

Data Index: 8076775 (Open Web Text)

Max Activating Token Index: 1004

Text #7

Max Range: 6.3696. Min Range: -6.3696

Max Act: 5.7859. Min Act: -0.1700

Data Index: 5039105 (Open Web Text)

Max Activating Token Index: 690

Text #8

Max Range: 6.3696. Min Range: -6.3696

Max Act: 5.8279. Min Act: -0.1700

Data Index: 3814066 (Open Web Text)

Max Activating Token Index: 992

Text #9

Max Range: 6.3696. Min Range: -6.3696

Max Act: 5.7457. Min Act: -0.1700

Data Index: 7392458 (Open Web Text)

Max Activating Token Index: 937

Text #10

Max Range: 6.3696. Min Range: -6.3696

Max Act: 5.8206. Min Act: -0.1700

Data Index: 1942621 (Open Web Text)

Max Activating Token Index: 424

Text #11

Max Range: 6.3696. Min Range: -6.3696

Max Act: 5.7436. Min Act: -0.1700

Data Index: 7089762 (Open Web Text)

Max Activating Token Index: 179

Text #12

Max Range: 6.3696. Min Range: -6.3696

Max Act: 5.7676. Min Act: -0.1700

Data Index: 6032012 (Open Web Text)

Max Activating Token Index: 212

Text #13

Max Range: 6.3696. Min Range: -6.3696

Max Act: 5.6925. Min Act: -0.1700

Data Index: 8158473 (Open Web Text)

Max Activating Token Index: 153

Text #14

Max Range: 6.3696. Min Range: -6.3696

Max Act: 5.7414. Min Act: -0.1700

Data Index: 6929657 (Open Web Text)

Max Activating Token Index: 277

Text #15

Max Range: 6.3696. Min Range: -6.3696

Max Act: 5.6571. Min Act: -0.1700

Data Index: 4622269 (Open Web Text)

Max Activating Token Index: 607

Text #16

Max Range: 6.3696. Min Range: -6.3696

Max Act: 5.6924. Min Act: -0.1700

Data Index: 8094485 (Open Web Text)

Max Activating Token Index: 612

Text #17

Max Range: 6.3696. Min Range: -6.3696

Max Act: 5.6484. Min Act: -0.1700

Data Index: 6563191 (Open Web Text)

Max Activating Token Index: 314

Text #18

Max Range: 6.3696. Min Range: -6.3696

Max Act: 5.6435. Min Act: -0.1700

Data Index: 1747996 (Open Web Text)

Max Activating Token Index: 819

Text #19

Max Range: 6.3696. Min Range: -6.3696

Max Act: 5.6834. Min Act: -0.1700

Data Index: 7464482 (Open Web Text)

Max Activating Token Index: 700