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

Dataset: Open Web Text

Neuron 1445 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: 5.3285. Min Range: -5.3285

Max Act: 5.3285. Min Act: -0.1700

Data Index: 5933459 (Open Web Text)

Max Activating Token Index: 724

Text #1

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.1339. Min Act: -0.1700

Data Index: 8297546 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.1292. Min Act: -0.1700

Data Index: 4310288 (Open Web Text)

Max Activating Token Index: 145

Text #3

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.1838. Min Act: -0.1700

Data Index: 3690816 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.1838. Min Act: -0.1700

Data Index: 3142967 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.1838. Min Act: -0.1700

Data Index: 5542158 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.1222. Min Act: -0.1700

Data Index: 7861571 (Open Web Text)

Max Activating Token Index: 117

Text #7

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.0614. Min Act: -0.1700

Data Index: 1892651 (Open Web Text)

Max Activating Token Index: 707

Text #8

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.0847. Min Act: -0.1700

Data Index: 2021263 (Open Web Text)

Max Activating Token Index: 8

Text #9

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.0853. Min Act: -0.1700

Data Index: 2153306 (Open Web Text)

Max Activating Token Index: 40

Text #10

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.1040. Min Act: -0.1700

Data Index: 7449468 (Open Web Text)

Max Activating Token Index: 101

Text #11

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.0459. Min Act: -0.1700

Data Index: 3020690 (Open Web Text)

Max Activating Token Index: 1020

Text #12

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.0247. Min Act: -0.1700

Data Index: 6490458 (Open Web Text)

Max Activating Token Index: 834

Text #13

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.0440. Min Act: -0.1700

Data Index: 5726718 (Open Web Text)

Max Activating Token Index: 158

Text #14

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.0106. Min Act: -0.1700

Data Index: 2600409 (Open Web Text)

Max Activating Token Index: 506

Text #15

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.0075. Min Act: -0.1700

Data Index: 7832992 (Open Web Text)

Max Activating Token Index: 469

Text #16

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.0371. Min Act: -0.1700

Data Index: 4261428 (Open Web Text)

Max Activating Token Index: 967

Text #17

Max Range: 5.3285. Min Range: -5.3285

Max Act: 4.9658. Min Act: -0.1700

Data Index: 5504956 (Open Web Text)

Max Activating Token Index: 621

Text #18

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.0342. Min Act: -0.1700

Data Index: 5541556 (Open Web Text)

Max Activating Token Index: 563

Text #19

Max Range: 5.3285. Min Range: -5.3285

Max Act: 5.0618. Min Act: -0.1700

Data Index: 4491811 (Open Web Text)

Max Activating Token Index: 704