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

Dataset: Open Web Text

Neuron 1778 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: 2.2980. Min Range: -2.2980

Max Act: 2.2980. Min Act: -0.1700

Data Index: 6526820 (Open Web Text)

Max Activating Token Index: 545

Text #1

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.2731. Min Act: -0.1700

Data Index: 3873357 (Open Web Text)

Max Activating Token Index: 249

Text #2

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.2511. Min Act: -0.1700

Data Index: 1342325 (Open Web Text)

Max Activating Token Index: 381

Text #3

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.2498. Min Act: -0.1700

Data Index: 7154657 (Open Web Text)

Max Activating Token Index: 509

Text #4

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.2064. Min Act: -0.1700

Data Index: 569869 (Open Web Text)

Max Activating Token Index: 53

Text #5

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.2050. Min Act: -0.1700

Data Index: 815803 (Open Web Text)

Max Activating Token Index: 158

Text #6

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.2290. Min Act: -0.1700

Data Index: 2099008 (Open Web Text)

Max Activating Token Index: 674

Text #7

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.1952. Min Act: -0.1700

Data Index: 606039 (Open Web Text)

Max Activating Token Index: 736

Text #8

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.2023. Min Act: -0.1700

Data Index: 6443854 (Open Web Text)

Max Activating Token Index: 703

Text #9

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.1913. Min Act: -0.1700

Data Index: 1730657 (Open Web Text)

Max Activating Token Index: 515

Text #10

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.1961. Min Act: -0.1700

Data Index: 5140576 (Open Web Text)

Max Activating Token Index: 737

Text #11

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.1988. Min Act: -0.1700

Data Index: 8778702 (Open Web Text)

Max Activating Token Index: 453

Text #12

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.1735. Min Act: -0.1700

Data Index: 5778330 (Open Web Text)

Max Activating Token Index: 205

Text #13

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.1848. Min Act: -0.1700

Data Index: 4746876 (Open Web Text)

Max Activating Token Index: 658

Text #14

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.1832. Min Act: -0.1700

Data Index: 3998791 (Open Web Text)

Max Activating Token Index: 506

Text #15

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.1536. Min Act: -0.1700

Data Index: 4649590 (Open Web Text)

Max Activating Token Index: 860

Text #16

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.1644. Min Act: -0.1700

Data Index: 5127189 (Open Web Text)

Max Activating Token Index: 438

Text #17

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.1690. Min Act: -0.1700

Data Index: 4665762 (Open Web Text)

Max Activating Token Index: 186

Text #18

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.1610. Min Act: -0.1700

Data Index: 2490117 (Open Web Text)

Max Activating Token Index: 833

Text #19

Max Range: 2.2980. Min Range: -2.2980

Max Act: 2.1574. Min Act: -0.1700

Data Index: 4009981 (Open Web Text)

Max Activating Token Index: 579