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

Dataset: Open Web Text

Neuron 698 in Layer 1

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: 4.3643. Min Range: -4.3643

Max Act: 4.3643. Min Act: -0.1700

Data Index: 5129696 (Open Web Text)

Max Activating Token Index: 569

Text #1

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.3279. Min Act: -0.1700

Data Index: 580877 (Open Web Text)

Max Activating Token Index: 716

Text #2

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.3370. Min Act: -0.1700

Data Index: 4543077 (Open Web Text)

Max Activating Token Index: 948

Text #3

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.3087. Min Act: -0.1700

Data Index: 3315337 (Open Web Text)

Max Activating Token Index: 550

Text #4

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.3285. Min Act: -0.1700

Data Index: 5137508 (Open Web Text)

Max Activating Token Index: 584

Text #5

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.3072. Min Act: -0.1700

Data Index: 8518112 (Open Web Text)

Max Activating Token Index: 980

Text #6

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.3166. Min Act: -0.1700

Data Index: 2201899 (Open Web Text)

Max Activating Token Index: 607

Text #7

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.3082. Min Act: -0.1700

Data Index: 8094271 (Open Web Text)

Max Activating Token Index: 746

Text #8

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2879. Min Act: -0.1700

Data Index: 4393670 (Open Web Text)

Max Activating Token Index: 648

Text #9

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2948. Min Act: -0.1700

Data Index: 7940858 (Open Web Text)

Max Activating Token Index: 46

Text #10

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2864. Min Act: -0.1700

Data Index: 4255174 (Open Web Text)

Max Activating Token Index: 451

Text #11

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2892. Min Act: -0.1700

Data Index: 7558347 (Open Web Text)

Max Activating Token Index: 429

Text #12

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2976. Min Act: -0.1700

Data Index: 5400490 (Open Web Text)

Max Activating Token Index: 460

Text #13

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2761. Min Act: -0.1700

Data Index: 5463842 (Open Web Text)

Max Activating Token Index: 660

Text #14

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2789. Min Act: -0.1700

Data Index: 8526661 (Open Web Text)

Max Activating Token Index: 365

Text #15

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2702. Min Act: -0.1700

Data Index: 2877254 (Open Web Text)

Max Activating Token Index: 462

Text #16

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2555. Min Act: -0.1700

Data Index: 1265508 (Open Web Text)

Max Activating Token Index: 949

Text #17

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2507. Min Act: -0.1700

Data Index: 5755757 (Open Web Text)

Max Activating Token Index: 133

Text #18

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2609. Min Act: -0.1700

Data Index: 2763321 (Open Web Text)

Max Activating Token Index: 542

Text #19

Max Range: 4.3643. Min Range: -4.3643

Max Act: 4.2293. Min Act: -0.1700

Data Index: 6353918 (Open Web Text)

Max Activating Token Index: 738