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

Dataset: Open Web Text

Neuron 1299 in Layer 0

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: 4.9273. Min Range: -4.9273

Max Act: 4.9273. Min Act: -0.1700

Data Index: 4116571 (Open Web Text)

Max Activating Token Index: 59

Text #1

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.9155. Min Act: -0.1700

Data Index: 6199429 (Open Web Text)

Max Activating Token Index: 894

Text #2

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.8445. Min Act: -0.1700

Data Index: 7625371 (Open Web Text)

Max Activating Token Index: 18

Text #3

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.8337. Min Act: -0.1700

Data Index: 2131199 (Open Web Text)

Max Activating Token Index: 34

Text #4

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.8092. Min Act: -0.1700

Data Index: 4627021 (Open Web Text)

Max Activating Token Index: 958

Text #5

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.7978. Min Act: -0.1700

Data Index: 1788780 (Open Web Text)

Max Activating Token Index: 33

Text #6

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.8227. Min Act: -0.1700

Data Index: 3920639 (Open Web Text)

Max Activating Token Index: 522

Text #7

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.7335. Min Act: -0.1700

Data Index: 7810683 (Open Web Text)

Max Activating Token Index: 951

Text #8

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.7819. Min Act: -0.1700

Data Index: 6219601 (Open Web Text)

Max Activating Token Index: 49

Text #9

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.7681. Min Act: -0.1700

Data Index: 6958802 (Open Web Text)

Max Activating Token Index: 213

Text #10

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.8207. Min Act: -0.1700

Data Index: 8422815 (Open Web Text)

Max Activating Token Index: 962

Text #11

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.7325. Min Act: -0.1700

Data Index: 4124065 (Open Web Text)

Max Activating Token Index: 24

Text #12

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.7228. Min Act: -0.1700

Data Index: 5406399 (Open Web Text)

Max Activating Token Index: 696

Text #13

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.7385. Min Act: -0.1700

Data Index: 5072482 (Open Web Text)

Max Activating Token Index: 18

Text #14

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.7273. Min Act: -0.1700

Data Index: 3332789 (Open Web Text)

Max Activating Token Index: 492

Text #15

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.7305. Min Act: -0.1700

Data Index: 3168995 (Open Web Text)

Max Activating Token Index: 57

Text #16

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.7503. Min Act: -0.1700

Data Index: 6651647 (Open Web Text)

Max Activating Token Index: 38

Text #17

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.7197. Min Act: -0.1700

Data Index: 7293368 (Open Web Text)

Max Activating Token Index: 1005

Text #18

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.6908. Min Act: -0.1700

Data Index: 7332026 (Open Web Text)

Max Activating Token Index: 892

Text #19

Max Range: 4.9273. Min Range: -4.9273

Max Act: 4.7071. Min Act: -0.1700

Data Index: 4036864 (Open Web Text)

Max Activating Token Index: 963