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

Dataset: Open Web Text

Neuron 882 in Layer 0

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: 1.4493. Min Range: -1.4493

Max Act: 1.4493. Min Act: -0.0132

Data Index: 5848540 (Open Web Text)

Max Activating Token Index: 452

Text #1

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.4454. Min Act: -0.1698

Data Index: 4546949 (Open Web Text)

Max Activating Token Index: 835

Text #2

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.4237. Min Act: 0.0462

Data Index: 6991389 (Open Web Text)

Max Activating Token Index: 399

Text #3

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.4194. Min Act: -0.0866

Data Index: 6423533 (Open Web Text)

Max Activating Token Index: 841

Text #4

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.4109. Min Act: -0.1692

Data Index: 1151054 (Open Web Text)

Max Activating Token Index: 787

Text #5

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3937. Min Act: -0.1434

Data Index: 5790799 (Open Web Text)

Max Activating Token Index: 797

Text #6

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.4012. Min Act: -0.1663

Data Index: 5838312 (Open Web Text)

Max Activating Token Index: 392

Text #7

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3957. Min Act: -0.0946

Data Index: 5147586 (Open Web Text)

Max Activating Token Index: 734

Text #8

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3962. Min Act: -0.1613

Data Index: 5780859 (Open Web Text)

Max Activating Token Index: 380

Text #9

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3961. Min Act: -0.1653

Data Index: 1871615 (Open Web Text)

Max Activating Token Index: 926

Text #10

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.4029. Min Act: -0.1700

Data Index: 1553561 (Open Web Text)

Max Activating Token Index: 619

Text #11

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3926. Min Act: -0.1300

Data Index: 6906573 (Open Web Text)

Max Activating Token Index: 842

Text #12

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3883. Min Act: -0.1460

Data Index: 1537963 (Open Web Text)

Max Activating Token Index: 413

Text #13

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3897. Min Act: -0.1552

Data Index: 5532327 (Open Web Text)

Max Activating Token Index: 616

Text #14

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3759. Min Act: -0.1533

Data Index: 6893978 (Open Web Text)

Max Activating Token Index: 376

Text #15

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3783. Min Act: -0.1699

Data Index: 4354178 (Open Web Text)

Max Activating Token Index: 598

Text #16

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3836. Min Act: -0.1688

Data Index: 3705096 (Open Web Text)

Max Activating Token Index: 542

Text #17

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3750. Min Act: -0.1119

Data Index: 7208982 (Open Web Text)

Max Activating Token Index: 693

Text #18

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3717. Min Act: -0.1260

Data Index: 3779204 (Open Web Text)

Max Activating Token Index: 613

Text #19

Max Range: 1.4493. Min Range: -1.4493

Max Act: 1.3650. Min Act: -0.1465

Data Index: 7751039 (Open Web Text)

Max Activating Token Index: 383