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

Dataset: Open Web Text

Neuron 1433 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: 3.9588. Min Range: -3.9588

Max Act: 3.9588. Min Act: -0.1700

Data Index: 8099207 (Open Web Text)

Max Activating Token Index: 415

Text #1

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.8981. Min Act: -0.1700

Data Index: 1010592 (Open Web Text)

Max Activating Token Index: 133

Text #2

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.8678. Min Act: -0.1700

Data Index: 5714643 (Open Web Text)

Max Activating Token Index: 381

Text #3

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.8712. Min Act: -0.1700

Data Index: 8439628 (Open Web Text)

Max Activating Token Index: 671

Text #4

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.8275. Min Act: -0.1700

Data Index: 6896166 (Open Web Text)

Max Activating Token Index: 260

Text #5

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.7575. Min Act: -0.1700

Data Index: 6148135 (Open Web Text)

Max Activating Token Index: 608

Text #6

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.7872. Min Act: -0.1700

Data Index: 5809126 (Open Web Text)

Max Activating Token Index: 996

Text #7

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.7774. Min Act: -0.1700

Data Index: 5816 (Open Web Text)

Max Activating Token Index: 310

Text #8

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.7284. Min Act: -0.1700

Data Index: 2864111 (Open Web Text)

Max Activating Token Index: 903

Text #9

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.6989. Min Act: -0.1700

Data Index: 8333910 (Open Web Text)

Max Activating Token Index: 864

Text #10

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.7168. Min Act: -0.1700

Data Index: 1150365 (Open Web Text)

Max Activating Token Index: 296

Text #11

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.6940. Min Act: -0.1700

Data Index: 3943115 (Open Web Text)

Max Activating Token Index: 242

Text #12

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.6652. Min Act: -0.1700

Data Index: 8505573 (Open Web Text)

Max Activating Token Index: 279

Text #13

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.6836. Min Act: -0.1700

Data Index: 4783113 (Open Web Text)

Max Activating Token Index: 106

Text #14

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.6905. Min Act: -0.1700

Data Index: 6526358 (Open Web Text)

Max Activating Token Index: 636

Text #15

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.6111. Min Act: -0.1700

Data Index: 6749927 (Open Web Text)

Max Activating Token Index: 275

Text #16

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.6446. Min Act: -0.1700

Data Index: 2073887 (Open Web Text)

Max Activating Token Index: 77

Text #17

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.5936. Min Act: -0.1700

Data Index: 4200177 (Open Web Text)

Max Activating Token Index: 177

Text #18

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.6396. Min Act: -0.1700

Data Index: 954018 (Open Web Text)

Max Activating Token Index: 289

Text #19

Max Range: 3.9588. Min Range: -3.9588

Max Act: 3.6529. Min Act: -0.1700

Data Index: 6879962 (Open Web Text)

Max Activating Token Index: 292