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

Dataset: Open Web Text

Neuron 98 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: 4.6458. Min Range: -4.6458

Max Act: 4.6251. Min Act: -0.1700

Data Index: 2859626 (Open Web Text)

Max Activating Token Index: 783

Text #1

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.6114. Min Act: -0.1700

Data Index: 8135574 (Open Web Text)

Max Activating Token Index: 441

Text #2

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.6458. Min Act: -0.1700

Data Index: 2422796 (Open Web Text)

Max Activating Token Index: 565

Text #3

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.6243. Min Act: -0.1700

Data Index: 8293917 (Open Web Text)

Max Activating Token Index: 986

Text #4

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.6074. Min Act: -0.1700

Data Index: 5775237 (Open Web Text)

Max Activating Token Index: 588

Text #5

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.5821. Min Act: -0.1700

Data Index: 5141566 (Open Web Text)

Max Activating Token Index: 682

Text #6

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.5834. Min Act: -0.1700

Data Index: 729521 (Open Web Text)

Max Activating Token Index: 98

Text #7

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.5743. Min Act: -0.1700

Data Index: 1806918 (Open Web Text)

Max Activating Token Index: 532

Text #8

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.5352. Min Act: -0.1700

Data Index: 1991217 (Open Web Text)

Max Activating Token Index: 895

Text #9

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.5689. Min Act: -0.1700

Data Index: 1504277 (Open Web Text)

Max Activating Token Index: 481

Text #10

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.5664. Min Act: -0.1700

Data Index: 7211720 (Open Web Text)

Max Activating Token Index: 631

Text #11

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.5719. Min Act: -0.1700

Data Index: 8708432 (Open Web Text)

Max Activating Token Index: 454

Text #12

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.5481. Min Act: -0.1700

Data Index: 1713856 (Open Web Text)

Max Activating Token Index: 33

Text #13

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.5417. Min Act: -0.1700

Data Index: 5033001 (Open Web Text)

Max Activating Token Index: 261

Text #14

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.5577. Min Act: -0.1700

Data Index: 1012362 (Open Web Text)

Max Activating Token Index: 618

Text #15

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.5340. Min Act: -0.1700

Data Index: 6683642 (Open Web Text)

Max Activating Token Index: 125

Text #16

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.5209. Min Act: -0.1700

Data Index: 184436 (Open Web Text)

Max Activating Token Index: 355

Text #17

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.5437. Min Act: -0.1700

Data Index: 3346980 (Open Web Text)

Max Activating Token Index: 92

Text #18

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.5560. Min Act: -0.1700

Data Index: 3871609 (Open Web Text)

Max Activating Token Index: 968

Text #19

Max Range: 4.6458. Min Range: -4.6458

Max Act: 4.5118. Min Act: -0.1700

Data Index: 162503 (Open Web Text)

Max Activating Token Index: 634