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

Dataset: Open Web Text

Neuron 621 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: 3.5490. Min Range: -3.5490

Max Act: 3.5490. Min Act: -0.1700

Data Index: 264129 (Open Web Text)

Max Activating Token Index: 942

Text #1

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.4869. Min Act: -0.1700

Data Index: 5682960 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.4357. Min Act: -0.1700

Data Index: 7207605 (Open Web Text)

Max Activating Token Index: 643

Text #3

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.4406. Min Act: -0.1700

Data Index: 2320455 (Open Web Text)

Max Activating Token Index: 746

Text #4

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.4516. Min Act: -0.1700

Data Index: 7551174 (Open Web Text)

Max Activating Token Index: 821

Text #5

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.3613. Min Act: -0.1700

Data Index: 8170301 (Open Web Text)

Max Activating Token Index: 10

Text #6

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.3089. Min Act: -0.1700

Data Index: 2363379 (Open Web Text)

Max Activating Token Index: 240

Text #7

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.2854. Min Act: -0.1700

Data Index: 1363521 (Open Web Text)

Max Activating Token Index: 234

Text #8

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.2376. Min Act: -0.1700

Data Index: 7015582 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.2400. Min Act: -0.1700

Data Index: 4728178 (Open Web Text)

Max Activating Token Index: 41

Text #10

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.2394. Min Act: -0.1700

Data Index: 89915 (Open Web Text)

Max Activating Token Index: 14

Text #11

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.2136. Min Act: -0.1700

Data Index: 132641 (Open Web Text)

Max Activating Token Index: 1023

Text #12

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.1995. Min Act: -0.1700

Data Index: 3815990 (Open Web Text)

Max Activating Token Index: 64

Text #13

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.1669. Min Act: -0.1700

Data Index: 5621999 (Open Web Text)

Max Activating Token Index: 201

Text #14

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.1649. Min Act: -0.1700

Data Index: 2329455 (Open Web Text)

Max Activating Token Index: 277

Text #15

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.1174. Min Act: -0.1700

Data Index: 5513211 (Open Web Text)

Max Activating Token Index: 105

Text #16

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.1170. Min Act: -0.1700

Data Index: 2661330 (Open Web Text)

Max Activating Token Index: 211

Text #17

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.1295. Min Act: -0.1700

Data Index: 4298532 (Open Web Text)

Max Activating Token Index: 73

Text #18

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.1102. Min Act: -0.1700

Data Index: 8336363 (Open Web Text)

Max Activating Token Index: 211

Text #19

Max Range: 3.5490. Min Range: -3.5490

Max Act: 3.0957. Min Act: -0.1700

Data Index: 6742934 (Open Web Text)

Max Activating Token Index: 517