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

Dataset: Open Web Text

Neuron 2120 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: 0.9169. Min Range: -0.9169

Max Act: 0.9169. Min Act: -0.1699

Data Index: 5716306 (Open Web Text)

Max Activating Token Index: 183

Text #1

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.9053. Min Act: -0.1699

Data Index: 7647673 (Open Web Text)

Max Activating Token Index: 152

Text #2

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8829. Min Act: -0.1698

Data Index: 1495652 (Open Web Text)

Max Activating Token Index: 188

Text #3

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8737. Min Act: -0.1700

Data Index: 7650396 (Open Web Text)

Max Activating Token Index: 289

Text #4

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8768. Min Act: -0.1695

Data Index: 8600330 (Open Web Text)

Max Activating Token Index: 410

Text #5

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8737. Min Act: -0.1700

Data Index: 6090316 (Open Web Text)

Max Activating Token Index: 810

Text #6

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8557. Min Act: -0.1699

Data Index: 2670878 (Open Web Text)

Max Activating Token Index: 352

Text #7

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8647. Min Act: -0.1700

Data Index: 1542492 (Open Web Text)

Max Activating Token Index: 519

Text #8

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8532. Min Act: -0.1697

Data Index: 3993572 (Open Web Text)

Max Activating Token Index: 156

Text #9

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8419. Min Act: -0.1700

Data Index: 2571902 (Open Web Text)

Max Activating Token Index: 661

Text #10

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8359. Min Act: -0.1700

Data Index: 1023437 (Open Web Text)

Max Activating Token Index: 904

Text #11

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8258. Min Act: -0.1700

Data Index: 65973 (Open Web Text)

Max Activating Token Index: 306

Text #12

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8288. Min Act: -0.1700

Data Index: 6228647 (Open Web Text)

Max Activating Token Index: 261

Text #13

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8200. Min Act: -0.1700

Data Index: 1315316 (Open Web Text)

Max Activating Token Index: 309

Text #14

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8356. Min Act: -0.1699

Data Index: 973215 (Open Web Text)

Max Activating Token Index: 101

Text #15

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8345. Min Act: -0.1700

Data Index: 6693289 (Open Web Text)

Max Activating Token Index: 549

Text #16

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8249. Min Act: -0.1700

Data Index: 6896727 (Open Web Text)

Max Activating Token Index: 166

Text #17

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8206. Min Act: -0.1700

Data Index: 1762214 (Open Web Text)

Max Activating Token Index: 325

Text #18

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8094. Min Act: -0.1698

Data Index: 6240127 (Open Web Text)

Max Activating Token Index: 688

Text #19

Max Range: 0.9169. Min Range: -0.9169

Max Act: 0.8117. Min Act: -0.1700

Data Index: 3419892 (Open Web Text)

Max Activating Token Index: 412