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

Dataset: Open Web Text

Neuron 1766 in Layer 3

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: 1.9634. Min Range: -1.9634

Max Act: 1.9634. Min Act: -0.1700

Data Index: 3821719 (Open Web Text)

Max Activating Token Index: 196

Text #1

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.9037. Min Act: -0.1700

Data Index: 6114216 (Open Web Text)

Max Activating Token Index: 208

Text #2

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.9040. Min Act: -0.1700

Data Index: 1408355 (Open Web Text)

Max Activating Token Index: 970

Text #3

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.8808. Min Act: -0.1700

Data Index: 8579990 (Open Web Text)

Max Activating Token Index: 351

Text #4

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.8850. Min Act: -0.1700

Data Index: 1539008 (Open Web Text)

Max Activating Token Index: 463

Text #5

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.8847. Min Act: -0.1700

Data Index: 1564351 (Open Web Text)

Max Activating Token Index: 70

Text #6

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.8418. Min Act: -0.1700

Data Index: 1729101 (Open Web Text)

Max Activating Token Index: 166

Text #7

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.8511. Min Act: -0.1700

Data Index: 2875243 (Open Web Text)

Max Activating Token Index: 253

Text #8

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.8809. Min Act: -0.1700

Data Index: 7626648 (Open Web Text)

Max Activating Token Index: 70

Text #9

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.8546. Min Act: -0.1700

Data Index: 8667523 (Open Web Text)

Max Activating Token Index: 930

Text #10

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.8425. Min Act: -0.1700

Data Index: 7694353 (Open Web Text)

Max Activating Token Index: 450

Text #11

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.8560. Min Act: -0.1700

Data Index: 4184701 (Open Web Text)

Max Activating Token Index: 885

Text #12

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.8375. Min Act: -0.1699

Data Index: 3953569 (Open Web Text)

Max Activating Token Index: 958

Text #13

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.8259. Min Act: -0.1700

Data Index: 2447442 (Open Web Text)

Max Activating Token Index: 473

Text #14

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.7954. Min Act: -0.1700

Data Index: 2399110 (Open Web Text)

Max Activating Token Index: 184

Text #15

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.8418. Min Act: -0.1700

Data Index: 2059613 (Open Web Text)

Max Activating Token Index: 534

Text #16

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.7809. Min Act: -0.1699

Data Index: 4753639 (Open Web Text)

Max Activating Token Index: 813

Text #17

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.8028. Min Act: -0.1700

Data Index: 1463261 (Open Web Text)

Max Activating Token Index: 212

Text #18

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.7863. Min Act: -0.1700

Data Index: 1967373 (Open Web Text)

Max Activating Token Index: 393

Text #19

Max Range: 1.9634. Min Range: -1.9634

Max Act: 1.7580. Min Act: -0.1700

Data Index: 1132812 (Open Web Text)

Max Activating Token Index: 382