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

Dataset: Open Web Text

Neuron 1112 in Layer 5

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: 3.8677. Min Range: -3.8677

Max Act: 3.8677. Min Act: -0.1700

Data Index: 5869314 (Open Web Text)

Max Activating Token Index: 944

Text #1

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.6269. Min Act: -0.1700

Data Index: 7353474 (Open Web Text)

Max Activating Token Index: 349

Text #2

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.6000. Min Act: -0.1700

Data Index: 2065758 (Open Web Text)

Max Activating Token Index: 343

Text #3

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.4652. Min Act: -0.1700

Data Index: 5265911 (Open Web Text)

Max Activating Token Index: 566

Text #4

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.4592. Min Act: -0.1700

Data Index: 3742189 (Open Web Text)

Max Activating Token Index: 363

Text #5

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.4477. Min Act: -0.1700

Data Index: 6320503 (Open Web Text)

Max Activating Token Index: 955

Text #6

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.4601. Min Act: -0.1700

Data Index: 7919684 (Open Web Text)

Max Activating Token Index: 584

Text #7

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.4522. Min Act: -0.1700

Data Index: 1242077 (Open Web Text)

Max Activating Token Index: 1010

Text #8

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.4095. Min Act: -0.1700

Data Index: 6553946 (Open Web Text)

Max Activating Token Index: 933

Text #9

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.4072. Min Act: -0.1700

Data Index: 4178526 (Open Web Text)

Max Activating Token Index: 174

Text #10

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.4107. Min Act: -0.1700

Data Index: 4521999 (Open Web Text)

Max Activating Token Index: 647

Text #11

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.4084. Min Act: -0.1700

Data Index: 3489607 (Open Web Text)

Max Activating Token Index: 590

Text #12

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.4109. Min Act: -0.1700

Data Index: 5405991 (Open Web Text)

Max Activating Token Index: 990

Text #13

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.3833. Min Act: -0.1700

Data Index: 3560130 (Open Web Text)

Max Activating Token Index: 74

Text #14

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.3688. Min Act: -0.1700

Data Index: 5873404 (Open Web Text)

Max Activating Token Index: 548

Text #15

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.3630. Min Act: -0.1700

Data Index: 1239458 (Open Web Text)

Max Activating Token Index: 52

Text #16

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.3671. Min Act: -0.1700

Data Index: 3552603 (Open Web Text)

Max Activating Token Index: 221

Text #17

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.3595. Min Act: -0.1700

Data Index: 7060966 (Open Web Text)

Max Activating Token Index: 972

Text #18

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.3777. Min Act: -0.1700

Data Index: 3832716 (Open Web Text)

Max Activating Token Index: 751

Text #19

Max Range: 3.8677. Min Range: -3.8677

Max Act: 3.3715. Min Act: -0.1700

Data Index: 5378994 (Open Web Text)

Max Activating Token Index: 963