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

Dataset: Open Web Text

Neuron 1043 in Layer 1

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: 2.9228. Min Range: -2.9228

Max Act: 2.9196. Min Act: -0.1700

Data Index: 6689127 (Open Web Text)

Max Activating Token Index: 716

Text #1

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.9228. Min Act: -0.1700

Data Index: 3139055 (Open Web Text)

Max Activating Token Index: 229

Text #2

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.9154. Min Act: -0.1700

Data Index: 7664826 (Open Web Text)

Max Activating Token Index: 534

Text #3

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.9071. Min Act: -0.1700

Data Index: 8073266 (Open Web Text)

Max Activating Token Index: 669

Text #4

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.8864. Min Act: -0.1700

Data Index: 790633 (Open Web Text)

Max Activating Token Index: 229

Text #5

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.8608. Min Act: -0.1700

Data Index: 1297719 (Open Web Text)

Max Activating Token Index: 109

Text #6

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.8616. Min Act: -0.1700

Data Index: 3657010 (Open Web Text)

Max Activating Token Index: 678

Text #7

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.8785. Min Act: -0.1700

Data Index: 645165 (Open Web Text)

Max Activating Token Index: 427

Text #8

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.8430. Min Act: -0.1700

Data Index: 6679890 (Open Web Text)

Max Activating Token Index: 689

Text #9

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.8605. Min Act: -0.1700

Data Index: 894500 (Open Web Text)

Max Activating Token Index: 1020

Text #10

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.8676. Min Act: -0.1700

Data Index: 1700559 (Open Web Text)

Max Activating Token Index: 1021

Text #11

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.8455. Min Act: -0.1700

Data Index: 1458096 (Open Web Text)

Max Activating Token Index: 72

Text #12

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.8419. Min Act: -0.1700

Data Index: 3807260 (Open Web Text)

Max Activating Token Index: 401

Text #13

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.8493. Min Act: -0.1700

Data Index: 3376533 (Open Web Text)

Max Activating Token Index: 650

Text #14

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.8059. Min Act: -0.1700

Data Index: 7781046 (Open Web Text)

Max Activating Token Index: 488

Text #15

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.8230. Min Act: -0.1700

Data Index: 5697231 (Open Web Text)

Max Activating Token Index: 689

Text #16

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.8144. Min Act: -0.1700

Data Index: 4325388 (Open Web Text)

Max Activating Token Index: 371

Text #17

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.8069. Min Act: -0.1700

Data Index: 1673077 (Open Web Text)

Max Activating Token Index: 212

Text #18

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.7995. Min Act: -0.1700

Data Index: 1381837 (Open Web Text)

Max Activating Token Index: 552

Text #19

Max Range: 2.9228. Min Range: -2.9228

Max Act: 2.7955. Min Act: -0.1700

Data Index: 6932672 (Open Web Text)

Max Activating Token Index: 43