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

Dataset: Open Web Text

Neuron 25 in Layer 5

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: 5.2452. Min Range: -5.2452

Max Act: 5.2452. Min Act: -0.1700

Data Index: 2519102 (Open Web Text)

Max Activating Token Index: 911

Text #1

Max Range: 5.2452. Min Range: -5.2452

Max Act: 5.2070. Min Act: -0.1700

Data Index: 8111090 (Open Web Text)

Max Activating Token Index: 999

Text #2

Max Range: 5.2452. Min Range: -5.2452

Max Act: 5.1758. Min Act: -0.1700

Data Index: 1521012 (Open Web Text)

Max Activating Token Index: 369

Text #3

Max Range: 5.2452. Min Range: -5.2452

Max Act: 5.1636. Min Act: -0.1700

Data Index: 1477143 (Open Web Text)

Max Activating Token Index: 853

Text #4

Max Range: 5.2452. Min Range: -5.2452

Max Act: 5.1450. Min Act: -0.1700

Data Index: 5406491 (Open Web Text)

Max Activating Token Index: 843

Text #5

Max Range: 5.2452. Min Range: -5.2452

Max Act: 5.1636. Min Act: -0.1700

Data Index: 4215343 (Open Web Text)

Max Activating Token Index: 519

Text #6

Max Range: 5.2452. Min Range: -5.2452

Max Act: 5.1408. Min Act: -0.1700

Data Index: 2879283 (Open Web Text)

Max Activating Token Index: 601

Text #7

Max Range: 5.2452. Min Range: -5.2452

Max Act: 5.1294. Min Act: -0.1700

Data Index: 2569677 (Open Web Text)

Max Activating Token Index: 371

Text #8

Max Range: 5.2452. Min Range: -5.2452

Max Act: 5.0921. Min Act: -0.1700

Data Index: 5604302 (Open Web Text)

Max Activating Token Index: 977

Text #9

Max Range: 5.2452. Min Range: -5.2452

Max Act: 5.0944. Min Act: -0.1700

Data Index: 6211926 (Open Web Text)

Max Activating Token Index: 574

Text #10

Max Range: 5.2452. Min Range: -5.2452

Max Act: 5.0858. Min Act: -0.1700

Data Index: 951819 (Open Web Text)

Max Activating Token Index: 884

Text #11

Max Range: 5.2452. Min Range: -5.2452

Max Act: 5.0522. Min Act: -0.1700

Data Index: 3720865 (Open Web Text)

Max Activating Token Index: 411

Text #12

Max Range: 5.2452. Min Range: -5.2452

Max Act: 5.0486. Min Act: -0.1700

Data Index: 969395 (Open Web Text)

Max Activating Token Index: 309

Text #13

Max Range: 5.2452. Min Range: -5.2452

Max Act: 5.0559. Min Act: -0.1700

Data Index: 6601308 (Open Web Text)

Max Activating Token Index: 676

Text #14

Max Range: 5.2452. Min Range: -5.2452

Max Act: 4.9928. Min Act: -0.1700

Data Index: 2478024 (Open Web Text)

Max Activating Token Index: 497

Text #15

Max Range: 5.2452. Min Range: -5.2452

Max Act: 5.0053. Min Act: -0.1700

Data Index: 2135496 (Open Web Text)

Max Activating Token Index: 402

Text #16

Max Range: 5.2452. Min Range: -5.2452

Max Act: 4.9598. Min Act: -0.1700

Data Index: 5187744 (Open Web Text)

Max Activating Token Index: 687

Text #17

Max Range: 5.2452. Min Range: -5.2452

Max Act: 4.9633. Min Act: -0.1700

Data Index: 3227631 (Open Web Text)

Max Activating Token Index: 966

Text #18

Max Range: 5.2452. Min Range: -5.2452

Max Act: 4.9858. Min Act: -0.1700

Data Index: 2025982 (Open Web Text)

Max Activating Token Index: 523

Text #19

Max Range: 5.2452. Min Range: -5.2452

Max Act: 4.9805. Min Act: -0.1700

Data Index: 832658 (Open Web Text)

Max Activating Token Index: 862