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

Dataset: Open Web Text

Neuron 2832 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: 1.5976. Min Range: -1.5976

Max Act: 1.5976. Min Act: -0.1700

Data Index: 7460801 (Open Web Text)

Max Activating Token Index: 852

Text #1

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5911. Min Act: -0.1700

Data Index: 7601600 (Open Web Text)

Max Activating Token Index: 543

Text #2

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5678. Min Act: -0.1698

Data Index: 8147102 (Open Web Text)

Max Activating Token Index: 935

Text #3

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5478. Min Act: -0.1700

Data Index: 3249448 (Open Web Text)

Max Activating Token Index: 716

Text #4

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5493. Min Act: -0.1699

Data Index: 5165006 (Open Web Text)

Max Activating Token Index: 144

Text #5

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5476. Min Act: -0.1700

Data Index: 6912471 (Open Web Text)

Max Activating Token Index: 506

Text #6

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5321. Min Act: -0.1700

Data Index: 7774647 (Open Web Text)

Max Activating Token Index: 580

Text #7

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5300. Min Act: -0.1700

Data Index: 4418025 (Open Web Text)

Max Activating Token Index: 665

Text #8

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5181. Min Act: -0.1700

Data Index: 8703289 (Open Web Text)

Max Activating Token Index: 606

Text #9

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5150. Min Act: -0.1700

Data Index: 5052309 (Open Web Text)

Max Activating Token Index: 716

Text #10

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5200. Min Act: -0.1700

Data Index: 4387394 (Open Web Text)

Max Activating Token Index: 430

Text #11

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5248. Min Act: -0.1700

Data Index: 710549 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5228. Min Act: -0.1700

Data Index: 4497436 (Open Web Text)

Max Activating Token Index: 471

Text #13

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5276. Min Act: -0.1698

Data Index: 1751687 (Open Web Text)

Max Activating Token Index: 165

Text #14

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5169. Min Act: -0.1700

Data Index: 6218786 (Open Web Text)

Max Activating Token Index: 669

Text #15

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5163. Min Act: -0.1700

Data Index: 4776922 (Open Web Text)

Max Activating Token Index: 508

Text #16

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5233. Min Act: -0.1700

Data Index: 7058855 (Open Web Text)

Max Activating Token Index: 690

Text #17

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5034. Min Act: -0.1700

Data Index: 4468164 (Open Web Text)

Max Activating Token Index: 512

Text #18

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5052. Min Act: -0.1700

Data Index: 4586065 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 1.5976. Min Range: -1.5976

Max Act: 1.5146. Min Act: -0.1700

Data Index: 3047371 (Open Web Text)

Max Activating Token Index: 442