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

Dataset: Open Web Text

Neuron 1179 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: 2.6388. Min Range: -2.6388

Max Act: 2.6388. Min Act: -0.1700

Data Index: 7471800 (Open Web Text)

Max Activating Token Index: 1014

Text #1

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.5444. Min Act: -0.1700

Data Index: 1362142 (Open Web Text)

Max Activating Token Index: 663

Text #2

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.5331. Min Act: -0.1700

Data Index: 1376185 (Open Web Text)

Max Activating Token Index: 606

Text #3

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.5182. Min Act: -0.1700

Data Index: 8738727 (Open Web Text)

Max Activating Token Index: 506

Text #4

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.4768. Min Act: -0.1700

Data Index: 4266311 (Open Web Text)

Max Activating Token Index: 40

Text #5

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.3853. Min Act: -0.1700

Data Index: 6439906 (Open Web Text)

Max Activating Token Index: 417

Text #6

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.4384. Min Act: -0.1700

Data Index: 4902670 (Open Web Text)

Max Activating Token Index: 54

Text #7

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.3927. Min Act: -0.1700

Data Index: 1564196 (Open Web Text)

Max Activating Token Index: 364

Text #8

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.2862. Min Act: -0.1700

Data Index: 2198048 (Open Web Text)

Max Activating Token Index: 513

Text #9

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.3144. Min Act: -0.1700

Data Index: 7580719 (Open Web Text)

Max Activating Token Index: 579

Text #10

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.3680. Min Act: -0.1700

Data Index: 8212192 (Open Web Text)

Max Activating Token Index: 646

Text #11

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.4742. Min Act: -0.1700

Data Index: 1071323 (Open Web Text)

Max Activating Token Index: 853

Text #12

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.3636. Min Act: -0.1700

Data Index: 1667544 (Open Web Text)

Max Activating Token Index: 219

Text #13

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.3358. Min Act: -0.1700

Data Index: 1159958 (Open Web Text)

Max Activating Token Index: 388

Text #14

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.2957. Min Act: -0.1700

Data Index: 350382 (Open Web Text)

Max Activating Token Index: 961

Text #15

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.3819. Min Act: -0.1700

Data Index: 1200486 (Open Web Text)

Max Activating Token Index: 173

Text #16

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.3232. Min Act: -0.1700

Data Index: 8262550 (Open Web Text)

Max Activating Token Index: 321

Text #17

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.2270. Min Act: -0.1700

Data Index: 2600179 (Open Web Text)

Max Activating Token Index: 300

Text #18

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.3335. Min Act: -0.1700

Data Index: 6121276 (Open Web Text)

Max Activating Token Index: 164

Text #19

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.2747. Min Act: -0.1700

Data Index: 1003157 (Open Web Text)

Max Activating Token Index: 17