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

Dataset: Open Web Text

Neuron 2486 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: 4.0291. Min Range: -4.0291

Max Act: 4.0291. Min Act: -0.1700

Data Index: 4953513 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9920. Min Act: -0.1700

Data Index: 5344507 (Open Web Text)

Max Activating Token Index: 42

Text #2

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9371. Min Act: -0.1700

Data Index: 3388208 (Open Web Text)

Max Activating Token Index: 630

Text #3

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9230. Min Act: -0.1700

Data Index: 4522346 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9184. Min Act: -0.1700

Data Index: 8631314 (Open Web Text)

Max Activating Token Index: 783

Text #5

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9336. Min Act: -0.1700

Data Index: 1042274 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9336. Min Act: -0.1700

Data Index: 2430879 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9067. Min Act: -0.1700

Data Index: 2553792 (Open Web Text)

Max Activating Token Index: 772

Text #8

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9336. Min Act: -0.1700

Data Index: 278718 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9336. Min Act: -0.1700

Data Index: 2632858 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9048. Min Act: -0.1700

Data Index: 2872992 (Open Web Text)

Max Activating Token Index: 650

Text #11

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.8950. Min Act: -0.1700

Data Index: 513696 (Open Web Text)

Max Activating Token Index: 684

Text #12

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9336. Min Act: -0.1700

Data Index: 1311488 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9336. Min Act: -0.1700

Data Index: 648000 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9336. Min Act: -0.1700

Data Index: 1343915 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9336. Min Act: -0.1700

Data Index: 1591908 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9336. Min Act: -0.1700

Data Index: 13051 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9336. Min Act: -0.1700

Data Index: 3022971 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9336. Min Act: -0.1700

Data Index: 775920 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 4.0291. Min Range: -4.0291

Max Act: 3.9336. Min Act: -0.1700

Data Index: 1756422 (Open Web Text)

Max Activating Token Index: 2