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

Dataset: Open Web Text

Neuron 745 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: 3.9308. Min Range: -3.9308

Max Act: 3.9308. Min Act: -0.1700

Data Index: 3862197 (Open Web Text)

Max Activating Token Index: 662

Text #1

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.9271. Min Act: -0.1700

Data Index: 1904297 (Open Web Text)

Max Activating Token Index: 438

Text #2

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.9115. Min Act: -0.1700

Data Index: 3557643 (Open Web Text)

Max Activating Token Index: 823

Text #3

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.9009. Min Act: -0.1700

Data Index: 174770 (Open Web Text)

Max Activating Token Index: 957

Text #4

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8911. Min Act: -0.1700

Data Index: 6680868 (Open Web Text)

Max Activating Token Index: 445

Text #5

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8424. Min Act: -0.1700

Data Index: 4540777 (Open Web Text)

Max Activating Token Index: 767

Text #6

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8921. Min Act: -0.1700

Data Index: 3862196 (Open Web Text)

Max Activating Token Index: 172

Text #7

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8803. Min Act: -0.1700

Data Index: 1826929 (Open Web Text)

Max Activating Token Index: 101

Text #8

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8445. Min Act: -0.1700

Data Index: 2064564 (Open Web Text)

Max Activating Token Index: 568

Text #9

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8129. Min Act: -0.1700

Data Index: 5737232 (Open Web Text)

Max Activating Token Index: 434

Text #10

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8343. Min Act: -0.1700

Data Index: 3319613 (Open Web Text)

Max Activating Token Index: 810

Text #11

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8315. Min Act: -0.1700

Data Index: 4325923 (Open Web Text)

Max Activating Token Index: 557

Text #12

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8437. Min Act: -0.1700

Data Index: 864873 (Open Web Text)

Max Activating Token Index: 936

Text #13

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8518. Min Act: -0.1700

Data Index: 1590434 (Open Web Text)

Max Activating Token Index: 638

Text #14

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8316. Min Act: -0.1700

Data Index: 3745329 (Open Web Text)

Max Activating Token Index: 728

Text #15

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8200. Min Act: -0.1700

Data Index: 1162450 (Open Web Text)

Max Activating Token Index: 653

Text #16

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8253. Min Act: -0.1700

Data Index: 7819531 (Open Web Text)

Max Activating Token Index: 288

Text #17

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.8146. Min Act: -0.1700

Data Index: 1953554 (Open Web Text)

Max Activating Token Index: 650

Text #18

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.7972. Min Act: -0.1700

Data Index: 4308913 (Open Web Text)

Max Activating Token Index: 411

Text #19

Max Range: 3.9308. Min Range: -3.9308

Max Act: 3.7994. Min Act: -0.1700

Data Index: 5063482 (Open Web Text)

Max Activating Token Index: 576