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

Dataset: Open Web Text

Neuron 2321 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: 4.6287. Min Range: -4.6287

Max Act: 4.6287. Min Act: -0.1700

Data Index: 8346022 (Open Web Text)

Max Activating Token Index: 914

Text #1

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.5764. Min Act: -0.1700

Data Index: 4475205 (Open Web Text)

Max Activating Token Index: 403

Text #2

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.5570. Min Act: -0.1700

Data Index: 6905845 (Open Web Text)

Max Activating Token Index: 535

Text #3

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.5539. Min Act: -0.1700

Data Index: 5429409 (Open Web Text)

Max Activating Token Index: 803

Text #4

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.5322. Min Act: -0.1700

Data Index: 4162332 (Open Web Text)

Max Activating Token Index: 762

Text #5

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.5253. Min Act: -0.1700

Data Index: 7295491 (Open Web Text)

Max Activating Token Index: 141

Text #6

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.5184. Min Act: -0.1700

Data Index: 1959288 (Open Web Text)

Max Activating Token Index: 199

Text #7

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.5029. Min Act: -0.1700

Data Index: 1793403 (Open Web Text)

Max Activating Token Index: 187

Text #8

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.5078. Min Act: -0.1700

Data Index: 5650981 (Open Web Text)

Max Activating Token Index: 590

Text #9

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.5282. Min Act: -0.1700

Data Index: 2327298 (Open Web Text)

Max Activating Token Index: 300

Text #10

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.4744. Min Act: -0.1700

Data Index: 3375392 (Open Web Text)

Max Activating Token Index: 524

Text #11

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.4841. Min Act: -0.1700

Data Index: 6310238 (Open Web Text)

Max Activating Token Index: 197

Text #12

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.4917. Min Act: -0.1700

Data Index: 5315871 (Open Web Text)

Max Activating Token Index: 517

Text #13

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.4947. Min Act: -0.1700

Data Index: 2901668 (Open Web Text)

Max Activating Token Index: 670

Text #14

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.4985. Min Act: -0.1700

Data Index: 131835 (Open Web Text)

Max Activating Token Index: 197

Text #15

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.4806. Min Act: -0.1700

Data Index: 2425558 (Open Web Text)

Max Activating Token Index: 170

Text #16

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.4763. Min Act: -0.1700

Data Index: 2029421 (Open Web Text)

Max Activating Token Index: 270

Text #17

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.4950. Min Act: -0.1700

Data Index: 8108803 (Open Web Text)

Max Activating Token Index: 212

Text #18

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.4806. Min Act: -0.1700

Data Index: 303724 (Open Web Text)

Max Activating Token Index: 355

Text #19

Max Range: 4.6287. Min Range: -4.6287

Max Act: 4.4681. Min Act: -0.1700

Data Index: 4435578 (Open Web Text)

Max Activating Token Index: 41