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

Dataset: Open Web Text

Neuron 19 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: 5.9536. Min Range: -5.9536

Max Act: 5.9536. Min Act: -0.1700

Data Index: 5884677 (Open Web Text)

Max Activating Token Index: 44

Text #1

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.9147. Min Act: -0.1700

Data Index: 2461463 (Open Web Text)

Max Activating Token Index: 40

Text #2

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.8869. Min Act: -0.1700

Data Index: 167058 (Open Web Text)

Max Activating Token Index: 406

Text #3

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.8530. Min Act: -0.1700

Data Index: 5335934 (Open Web Text)

Max Activating Token Index: 39

Text #4

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.8712. Min Act: -0.1700

Data Index: 1012969 (Open Web Text)

Max Activating Token Index: 482

Text #5

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.8575. Min Act: -0.1700

Data Index: 6084495 (Open Web Text)

Max Activating Token Index: 761

Text #6

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.8643. Min Act: -0.1700

Data Index: 1612303 (Open Web Text)

Max Activating Token Index: 463

Text #7

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.8459. Min Act: -0.1700

Data Index: 8468073 (Open Web Text)

Max Activating Token Index: 116

Text #8

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.8671. Min Act: -0.1700

Data Index: 3529919 (Open Web Text)

Max Activating Token Index: 360

Text #9

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.8271. Min Act: -0.1700

Data Index: 8576665 (Open Web Text)

Max Activating Token Index: 217

Text #10

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.7981. Min Act: -0.1700

Data Index: 2209108 (Open Web Text)

Max Activating Token Index: 527

Text #11

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.8076. Min Act: -0.1700

Data Index: 1097508 (Open Web Text)

Max Activating Token Index: 577

Text #12

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.8033. Min Act: -0.1700

Data Index: 1379912 (Open Web Text)

Max Activating Token Index: 425

Text #13

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.7946. Min Act: -0.1700

Data Index: 2703993 (Open Web Text)

Max Activating Token Index: 118

Text #14

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.8057. Min Act: -0.1700

Data Index: 809243 (Open Web Text)

Max Activating Token Index: 878

Text #15

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.7927. Min Act: -0.1700

Data Index: 2699402 (Open Web Text)

Max Activating Token Index: 67

Text #16

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.7695. Min Act: -0.1700

Data Index: 6026836 (Open Web Text)

Max Activating Token Index: 569

Text #17

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.7425. Min Act: -0.1700

Data Index: 7600849 (Open Web Text)

Max Activating Token Index: 195

Text #18

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.7382. Min Act: -0.1700

Data Index: 8337761 (Open Web Text)

Max Activating Token Index: 501

Text #19

Max Range: 5.9536. Min Range: -5.9536

Max Act: 5.7526. Min Act: -0.1700

Data Index: 4100936 (Open Web Text)

Max Activating Token Index: 106