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

Dataset: Open Web Text

Neuron 2255 in Layer 3

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: 4.9727. Min Range: -4.9727

Max Act: 4.9727. Min Act: -0.1700

Data Index: 4340721 (Open Web Text)

Max Activating Token Index: 908

Text #1

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.8186. Min Act: -0.1700

Data Index: 3693839 (Open Web Text)

Max Activating Token Index: 465

Text #2

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.8321. Min Act: -0.1700

Data Index: 3700106 (Open Web Text)

Max Activating Token Index: 27

Text #3

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.7393. Min Act: -0.1700

Data Index: 3419186 (Open Web Text)

Max Activating Token Index: 658

Text #4

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.6551. Min Act: -0.1700

Data Index: 1014732 (Open Web Text)

Max Activating Token Index: 782

Text #5

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.7202. Min Act: -0.1700

Data Index: 2721117 (Open Web Text)

Max Activating Token Index: 355

Text #6

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.7088. Min Act: -0.1700

Data Index: 7287643 (Open Web Text)

Max Activating Token Index: 26

Text #7

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.6831. Min Act: -0.1700

Data Index: 2698478 (Open Web Text)

Max Activating Token Index: 901

Text #8

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.6974. Min Act: -0.1700

Data Index: 1700068 (Open Web Text)

Max Activating Token Index: 84

Text #9

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.6508. Min Act: -0.1700

Data Index: 8290646 (Open Web Text)

Max Activating Token Index: 981

Text #10

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.6493. Min Act: -0.1700

Data Index: 8751895 (Open Web Text)

Max Activating Token Index: 1014

Text #11

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.6293. Min Act: -0.1700

Data Index: 4389175 (Open Web Text)

Max Activating Token Index: 996

Text #12

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.6912. Min Act: -0.1700

Data Index: 8277378 (Open Web Text)

Max Activating Token Index: 796

Text #13

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.6326. Min Act: -0.1700

Data Index: 6319431 (Open Web Text)

Max Activating Token Index: 936

Text #14

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.6430. Min Act: -0.1700

Data Index: 3185965 (Open Web Text)

Max Activating Token Index: 416

Text #15

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.6483. Min Act: -0.1700

Data Index: 4510636 (Open Web Text)

Max Activating Token Index: 221

Text #16

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.6296. Min Act: -0.1700

Data Index: 2704008 (Open Web Text)

Max Activating Token Index: 510

Text #17

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.6067. Min Act: -0.1700

Data Index: 6657015 (Open Web Text)

Max Activating Token Index: 952

Text #18

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.6073. Min Act: -0.1700

Data Index: 2205524 (Open Web Text)

Max Activating Token Index: 567

Text #19

Max Range: 4.9727. Min Range: -4.9727

Max Act: 4.6022. Min Act: -0.1700

Data Index: 8305606 (Open Web Text)

Max Activating Token Index: 638