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

Dataset: Open Web Text

Neuron 105 in Layer 2

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: 3.3666. Min Range: -3.3666

Max Act: 3.3666. Min Act: -0.1700

Data Index: 4785002 (Open Web Text)

Max Activating Token Index: 679

Text #1

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.3337. Min Act: -0.1700

Data Index: 5505405 (Open Web Text)

Max Activating Token Index: 604

Text #2

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.3174. Min Act: -0.1700

Data Index: 7317159 (Open Web Text)

Max Activating Token Index: 949

Text #3

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2883. Min Act: -0.1700

Data Index: 3423067 (Open Web Text)

Max Activating Token Index: 446

Text #4

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2797. Min Act: -0.1700

Data Index: 1681367 (Open Web Text)

Max Activating Token Index: 787

Text #5

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2896. Min Act: -0.1700

Data Index: 794196 (Open Web Text)

Max Activating Token Index: 519

Text #6

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2775. Min Act: -0.1700

Data Index: 4583276 (Open Web Text)

Max Activating Token Index: 728

Text #7

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2666. Min Act: -0.1700

Data Index: 6467982 (Open Web Text)

Max Activating Token Index: 746

Text #8

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2516. Min Act: -0.1700

Data Index: 8476638 (Open Web Text)

Max Activating Token Index: 891

Text #9

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2316. Min Act: -0.1700

Data Index: 6452693 (Open Web Text)

Max Activating Token Index: 548

Text #10

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2506. Min Act: -0.1700

Data Index: 4236977 (Open Web Text)

Max Activating Token Index: 323

Text #11

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2417. Min Act: -0.1700

Data Index: 7939915 (Open Web Text)

Max Activating Token Index: 415

Text #12

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2404. Min Act: -0.1700

Data Index: 1466710 (Open Web Text)

Max Activating Token Index: 463

Text #13

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2167. Min Act: -0.1700

Data Index: 899036 (Open Web Text)

Max Activating Token Index: 186

Text #14

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2166. Min Act: -0.1700

Data Index: 2596119 (Open Web Text)

Max Activating Token Index: 319

Text #15

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2037. Min Act: -0.1700

Data Index: 3087583 (Open Web Text)

Max Activating Token Index: 881

Text #16

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2293. Min Act: -0.1700

Data Index: 968330 (Open Web Text)

Max Activating Token Index: 487

Text #17

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.1885. Min Act: -0.1700

Data Index: 3053052 (Open Web Text)

Max Activating Token Index: 331

Text #18

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2063. Min Act: -0.1700

Data Index: 4064116 (Open Web Text)

Max Activating Token Index: 293

Text #19

Max Range: 3.3666. Min Range: -3.3666

Max Act: 3.2066. Min Act: -0.1700

Data Index: 4901308 (Open Web Text)

Max Activating Token Index: 709