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

Dataset: Open Web Text

Neuron 2677 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: 3.8176. Min Range: -3.8176

Max Act: 3.8176. Min Act: -0.1700

Data Index: 1024614 (Open Web Text)

Max Activating Token Index: 982

Text #1

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7361. Min Act: -0.1700

Data Index: 1348873 (Open Web Text)

Max Activating Token Index: 214

Text #2

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6608. Min Act: -0.1700

Data Index: 6453762 (Open Web Text)

Max Activating Token Index: 536

Text #3

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6338. Min Act: -0.1700

Data Index: 2895715 (Open Web Text)

Max Activating Token Index: 400

Text #4

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.5458. Min Act: -0.1700

Data Index: 5590771 (Open Web Text)

Max Activating Token Index: 606

Text #5

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.5932. Min Act: -0.1700

Data Index: 60544 (Open Web Text)

Max Activating Token Index: 161

Text #6

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.5770. Min Act: -0.1700

Data Index: 767720 (Open Web Text)

Max Activating Token Index: 506

Text #7

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.5873. Min Act: -0.1700

Data Index: 3292240 (Open Web Text)

Max Activating Token Index: 958

Text #8

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.5956. Min Act: -0.1700

Data Index: 2712269 (Open Web Text)

Max Activating Token Index: 83

Text #9

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.5424. Min Act: -0.1700

Data Index: 3096289 (Open Web Text)

Max Activating Token Index: 636

Text #10

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.5913. Min Act: -0.1700

Data Index: 8612925 (Open Web Text)

Max Activating Token Index: 760

Text #11

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.5679. Min Act: -0.1700

Data Index: 8763976 (Open Web Text)

Max Activating Token Index: 74

Text #12

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.5385. Min Act: -0.1700

Data Index: 736065 (Open Web Text)

Max Activating Token Index: 445

Text #13

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.5416. Min Act: -0.1700

Data Index: 7568491 (Open Web Text)

Max Activating Token Index: 794

Text #14

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.5534. Min Act: -0.1700

Data Index: 1070767 (Open Web Text)

Max Activating Token Index: 875

Text #15

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.5511. Min Act: -0.1700

Data Index: 7064482 (Open Web Text)

Max Activating Token Index: 217

Text #16

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.5547. Min Act: -0.1700

Data Index: 6753121 (Open Web Text)

Max Activating Token Index: 234

Text #17

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.5248. Min Act: -0.1700

Data Index: 2732355 (Open Web Text)

Max Activating Token Index: 1001

Text #18

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.5183. Min Act: -0.1700

Data Index: 2416757 (Open Web Text)

Max Activating Token Index: 846

Text #19

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.5338. Min Act: -0.1700

Data Index: 7123926 (Open Web Text)

Max Activating Token Index: 1008