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

Dataset: Open Web Text

Neuron 1606 in Layer 6

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: 4.2634. Min Range: -4.2634

Max Act: 4.2634. Min Act: -0.1700

Data Index: 316975 (Open Web Text)

Max Activating Token Index: 686

Text #1

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.2241. Min Act: -0.1700

Data Index: 699695 (Open Web Text)

Max Activating Token Index: 358

Text #2

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.1709. Min Act: -0.1700

Data Index: 7180722 (Open Web Text)

Max Activating Token Index: 427

Text #3

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.1639. Min Act: -0.1700

Data Index: 2978670 (Open Web Text)

Max Activating Token Index: 532

Text #4

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.1298. Min Act: -0.1700

Data Index: 170922 (Open Web Text)

Max Activating Token Index: 254

Text #5

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0868. Min Act: -0.1700

Data Index: 4220591 (Open Web Text)

Max Activating Token Index: 843

Text #6

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0909. Min Act: -0.1700

Data Index: 5967690 (Open Web Text)

Max Activating Token Index: 416

Text #7

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.1007. Min Act: -0.1700

Data Index: 7108847 (Open Web Text)

Max Activating Token Index: 66

Text #8

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0507. Min Act: -0.1700

Data Index: 2440747 (Open Web Text)

Max Activating Token Index: 460

Text #9

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0358. Min Act: -0.1700

Data Index: 2024666 (Open Web Text)

Max Activating Token Index: 789

Text #10

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0459. Min Act: -0.1700

Data Index: 965856 (Open Web Text)

Max Activating Token Index: 832

Text #11

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0250. Min Act: -0.1700

Data Index: 547841 (Open Web Text)

Max Activating Token Index: 389

Text #12

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0418. Min Act: -0.1700

Data Index: 8543544 (Open Web Text)

Max Activating Token Index: 226

Text #13

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0359. Min Act: -0.1700

Data Index: 7948481 (Open Web Text)

Max Activating Token Index: 748

Text #14

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0450. Min Act: -0.1700

Data Index: 7839284 (Open Web Text)

Max Activating Token Index: 774

Text #15

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0166. Min Act: -0.1700

Data Index: 3380830 (Open Web Text)

Max Activating Token Index: 156

Text #16

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0584. Min Act: -0.1700

Data Index: 7359668 (Open Web Text)

Max Activating Token Index: 814

Text #17

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0526. Min Act: -0.1700

Data Index: 6893090 (Open Web Text)

Max Activating Token Index: 356

Text #18

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0266. Min Act: -0.1700

Data Index: 5869449 (Open Web Text)

Max Activating Token Index: 699

Text #19

Max Range: 4.2634. Min Range: -4.2634

Max Act: 4.0582. Min Act: -0.1700

Data Index: 2480779 (Open Web Text)

Max Activating Token Index: 353