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

Dataset: Open Web Text

Neuron 762 in Layer 4

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: 3.9851. Min Range: -3.9851

Max Act: 3.9851. Min Act: -0.1700

Data Index: 5738139 (Open Web Text)

Max Activating Token Index: 906

Text #1

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.7823. Min Act: -0.1700

Data Index: 8766266 (Open Web Text)

Max Activating Token Index: 591

Text #2

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.7379. Min Act: -0.1700

Data Index: 1718107 (Open Web Text)

Max Activating Token Index: 951

Text #3

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.7326. Min Act: -0.1700

Data Index: 177527 (Open Web Text)

Max Activating Token Index: 681

Text #4

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.7158. Min Act: -0.1700

Data Index: 1045380 (Open Web Text)

Max Activating Token Index: 458

Text #5

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.6754. Min Act: -0.1700

Data Index: 1196522 (Open Web Text)

Max Activating Token Index: 173

Text #6

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.6421. Min Act: -0.1700

Data Index: 1130339 (Open Web Text)

Max Activating Token Index: 62

Text #7

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.6284. Min Act: -0.1700

Data Index: 8261867 (Open Web Text)

Max Activating Token Index: 113

Text #8

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.6407. Min Act: -0.1700

Data Index: 441669 (Open Web Text)

Max Activating Token Index: 88

Text #9

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.5821. Min Act: -0.1700

Data Index: 2724565 (Open Web Text)

Max Activating Token Index: 117

Text #10

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.5585. Min Act: -0.1700

Data Index: 7519161 (Open Web Text)

Max Activating Token Index: 307

Text #11

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.5518. Min Act: -0.1700

Data Index: 4692694 (Open Web Text)

Max Activating Token Index: 410

Text #12

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.5063. Min Act: -0.1700

Data Index: 8696051 (Open Web Text)

Max Activating Token Index: 34

Text #13

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.5260. Min Act: -0.1700

Data Index: 7066886 (Open Web Text)

Max Activating Token Index: 765

Text #14

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.5010. Min Act: -0.1700

Data Index: 4191964 (Open Web Text)

Max Activating Token Index: 289

Text #15

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.4823. Min Act: -0.1700

Data Index: 7292616 (Open Web Text)

Max Activating Token Index: 174

Text #16

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.4933. Min Act: -0.1700

Data Index: 1938329 (Open Web Text)

Max Activating Token Index: 902

Text #17

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.4884. Min Act: -0.1700

Data Index: 4963541 (Open Web Text)

Max Activating Token Index: 817

Text #18

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.4922. Min Act: -0.1700

Data Index: 1785013 (Open Web Text)

Max Activating Token Index: 439

Text #19

Max Range: 3.9851. Min Range: -3.9851

Max Act: 3.5127. Min Act: -0.1700

Data Index: 1888841 (Open Web Text)

Max Activating Token Index: 498