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

Dataset: Open Web Text

Neuron 2350 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: 2.8513. Min Range: -2.8513

Max Act: 2.8513. Min Act: -0.1700

Data Index: 4052400 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7845. Min Act: -0.1700

Data Index: 2511672 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7718. Min Act: -0.1700

Data Index: 3149601 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7826. Min Act: -0.1700

Data Index: 4103382 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7728. Min Act: -0.1700

Data Index: 6336897 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7853. Min Act: -0.1700

Data Index: 6678704 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7776. Min Act: -0.1700

Data Index: 484263 (Open Web Text)

Max Activating Token Index: 19

Text #7

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7639. Min Act: -0.1700

Data Index: 6377131 (Open Web Text)

Max Activating Token Index: 23

Text #8

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7625. Min Act: -0.1700

Data Index: 6902722 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7552. Min Act: -0.1700

Data Index: 1685340 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7528. Min Act: -0.1700

Data Index: 525744 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7528. Min Act: -0.1700

Data Index: 525739 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7528. Min Act: -0.1700

Data Index: 171819 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7528. Min Act: -0.1700

Data Index: 509555 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7528. Min Act: -0.1700

Data Index: 305859 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7528. Min Act: -0.1700

Data Index: 95478 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7528. Min Act: -0.1700

Data Index: 165262 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7528. Min Act: -0.1700

Data Index: 281733 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7528. Min Act: -0.1700

Data Index: 30456 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 2.8513. Min Range: -2.8513

Max Act: 2.7528. Min Act: -0.1700

Data Index: 481242 (Open Web Text)

Max Activating Token Index: 3