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

Dataset: Open Web Text

Neuron 431 in Layer 6

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: 4.5901. Min Range: -4.5901

Max Act: 4.5901. Min Act: -0.1700

Data Index: 1423572 (Open Web Text)

Max Activating Token Index: 506

Text #1

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.5719. Min Act: -0.1700

Data Index: 8296654 (Open Web Text)

Max Activating Token Index: 309

Text #2

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.4768. Min Act: -0.1700

Data Index: 3158322 (Open Web Text)

Max Activating Token Index: 255

Text #3

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.4385. Min Act: -0.1700

Data Index: 8240273 (Open Web Text)

Max Activating Token Index: 731

Text #4

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.4581. Min Act: -0.1700

Data Index: 6091946 (Open Web Text)

Max Activating Token Index: 729

Text #5

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.4534. Min Act: -0.1700

Data Index: 6422922 (Open Web Text)

Max Activating Token Index: 434

Text #6

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.4349. Min Act: -0.1700

Data Index: 5123502 (Open Web Text)

Max Activating Token Index: 853

Text #7

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.4408. Min Act: -0.1700

Data Index: 7005255 (Open Web Text)

Max Activating Token Index: 397

Text #8

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.4257. Min Act: -0.1700

Data Index: 6571132 (Open Web Text)

Max Activating Token Index: 884

Text #9

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.3975. Min Act: -0.1700

Data Index: 1139016 (Open Web Text)

Max Activating Token Index: 649

Text #10

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.3721. Min Act: -0.1700

Data Index: 1141844 (Open Web Text)

Max Activating Token Index: 1013

Text #11

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.4000. Min Act: -0.1700

Data Index: 8199521 (Open Web Text)

Max Activating Token Index: 326

Text #12

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.3202. Min Act: -0.1700

Data Index: 8609189 (Open Web Text)

Max Activating Token Index: 382

Text #13

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.3260. Min Act: -0.1700

Data Index: 8342659 (Open Web Text)

Max Activating Token Index: 209

Text #14

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.2887. Min Act: -0.1700

Data Index: 4753086 (Open Web Text)

Max Activating Token Index: 781

Text #15

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.3113. Min Act: -0.1700

Data Index: 301807 (Open Web Text)

Max Activating Token Index: 450

Text #16

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.3823. Min Act: -0.1700

Data Index: 1047174 (Open Web Text)

Max Activating Token Index: 515

Text #17

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.3651. Min Act: -0.1700

Data Index: 3309390 (Open Web Text)

Max Activating Token Index: 645

Text #18

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.3538. Min Act: -0.1700

Data Index: 4865938 (Open Web Text)

Max Activating Token Index: 665

Text #19

Max Range: 4.5901. Min Range: -4.5901

Max Act: 4.3084. Min Act: -0.1700

Data Index: 7020086 (Open Web Text)

Max Activating Token Index: 423