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

Dataset: Open Web Text

Neuron 1760 in Layer 2

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: 2.1471. Min Range: -2.1471

Max Act: 2.1471. Min Act: -0.1700

Data Index: 5150994 (Open Web Text)

Max Activating Token Index: 167

Text #1

Max Range: 2.1471. Min Range: -2.1471

Max Act: 2.0450. Min Act: -0.1700

Data Index: 7002912 (Open Web Text)

Max Activating Token Index: 939

Text #2

Max Range: 2.1471. Min Range: -2.1471

Max Act: 2.0343. Min Act: -0.1700

Data Index: 3321882 (Open Web Text)

Max Activating Token Index: 48

Text #3

Max Range: 2.1471. Min Range: -2.1471

Max Act: 2.0182. Min Act: -0.1700

Data Index: 2992674 (Open Web Text)

Max Activating Token Index: 870

Text #4

Max Range: 2.1471. Min Range: -2.1471

Max Act: 2.0396. Min Act: -0.1700

Data Index: 8523520 (Open Web Text)

Max Activating Token Index: 1013

Text #5

Max Range: 2.1471. Min Range: -2.1471

Max Act: 2.0091. Min Act: -0.1700

Data Index: 7114673 (Open Web Text)

Max Activating Token Index: 227

Text #6

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.9906. Min Act: -0.1700

Data Index: 8065014 (Open Web Text)

Max Activating Token Index: 965

Text #7

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.9544. Min Act: -0.1700

Data Index: 7002913 (Open Web Text)

Max Activating Token Index: 919

Text #8

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.9828. Min Act: -0.1700

Data Index: 3321881 (Open Web Text)

Max Activating Token Index: 753

Text #9

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.9823. Min Act: -0.1700

Data Index: 5150995 (Open Web Text)

Max Activating Token Index: 453

Text #10

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.9553. Min Act: -0.1700

Data Index: 6324280 (Open Web Text)

Max Activating Token Index: 1023

Text #11

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.9415. Min Act: -0.1700

Data Index: 244721 (Open Web Text)

Max Activating Token Index: 853

Text #12

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.9382. Min Act: -0.1700

Data Index: 3142802 (Open Web Text)

Max Activating Token Index: 169

Text #13

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.9591. Min Act: -0.1700

Data Index: 6204707 (Open Web Text)

Max Activating Token Index: 168

Text #14

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.9399. Min Act: -0.1700

Data Index: 3891670 (Open Web Text)

Max Activating Token Index: 224

Text #15

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.9434. Min Act: -0.1700

Data Index: 2863789 (Open Web Text)

Max Activating Token Index: 269

Text #16

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.9220. Min Act: -0.1700

Data Index: 4983922 (Open Web Text)

Max Activating Token Index: 787

Text #17

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.9546. Min Act: -0.1700

Data Index: 2843165 (Open Web Text)

Max Activating Token Index: 574

Text #18

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.9172. Min Act: -0.1700

Data Index: 5156332 (Open Web Text)

Max Activating Token Index: 685

Text #19

Max Range: 2.1471. Min Range: -2.1471

Max Act: 1.9211. Min Act: -0.1700

Data Index: 658794 (Open Web Text)

Max Activating Token Index: 119