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

Dataset: Open Web Text

Neuron 2534 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: 3.8540. Min Range: -3.8540

Max Act: 3.8540. Min Act: -0.1700

Data Index: 1145831 (Open Web Text)

Max Activating Token Index: 39

Text #1

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.6132. Min Act: -0.1700

Data Index: 5985996 (Open Web Text)

Max Activating Token Index: 705

Text #2

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.5773. Min Act: -0.1700

Data Index: 1318969 (Open Web Text)

Max Activating Token Index: 74

Text #3

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.5709. Min Act: -0.1700

Data Index: 6368329 (Open Web Text)

Max Activating Token Index: 153

Text #4

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.5871. Min Act: -0.1700

Data Index: 1227379 (Open Web Text)

Max Activating Token Index: 213

Text #5

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.5520. Min Act: -0.1700

Data Index: 6782637 (Open Web Text)

Max Activating Token Index: 267

Text #6

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.5616. Min Act: -0.1700

Data Index: 3922300 (Open Web Text)

Max Activating Token Index: 53

Text #7

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.5268. Min Act: -0.1700

Data Index: 1849609 (Open Web Text)

Max Activating Token Index: 451

Text #8

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.5232. Min Act: -0.1700

Data Index: 4001537 (Open Web Text)

Max Activating Token Index: 952

Text #9

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.5135. Min Act: -0.1700

Data Index: 2870257 (Open Web Text)

Max Activating Token Index: 824

Text #10

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.4970. Min Act: -0.1700

Data Index: 5161148 (Open Web Text)

Max Activating Token Index: 663

Text #11

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.4999. Min Act: -0.1700

Data Index: 8540243 (Open Web Text)

Max Activating Token Index: 601

Text #12

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.4365. Min Act: -0.1700

Data Index: 5164075 (Open Web Text)

Max Activating Token Index: 980

Text #13

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.4395. Min Act: -0.1700

Data Index: 8359111 (Open Web Text)

Max Activating Token Index: 76

Text #14

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.4458. Min Act: -0.1700

Data Index: 1882523 (Open Web Text)

Max Activating Token Index: 685

Text #15

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.4382. Min Act: -0.1700

Data Index: 3719550 (Open Web Text)

Max Activating Token Index: 22

Text #16

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.4211. Min Act: -0.1700

Data Index: 8792985 (Open Web Text)

Max Activating Token Index: 13

Text #17

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.4008. Min Act: -0.1700

Data Index: 5697622 (Open Web Text)

Max Activating Token Index: 1008

Text #18

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.4242. Min Act: -0.1700

Data Index: 1556772 (Open Web Text)

Max Activating Token Index: 620

Text #19

Max Range: 3.8540. Min Range: -3.8540

Max Act: 3.4381. Min Act: -0.1700

Data Index: 6625525 (Open Web Text)

Max Activating Token Index: 22