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

Dataset: Open Web Text

Neuron 2623 in Layer 1

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: 1.5482. Min Range: -1.5482

Max Act: 1.5482. Min Act: -0.1699

Data Index: 2665069 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.5188. Min Act: -0.1699

Data Index: 3253722 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.5055. Min Act: -0.1696

Data Index: 8464551 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4749. Min Act: -0.1698

Data Index: 5018743 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4775. Min Act: -0.1697

Data Index: 5039497 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4775. Min Act: -0.1680

Data Index: 8666605 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4775. Min Act: -0.1690

Data Index: 3314261 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4775. Min Act: -0.1700

Data Index: 8331688 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4575. Min Act: -0.1700

Data Index: 1492160 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4534. Min Act: -0.1700

Data Index: 5737884 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4477. Min Act: -0.1698

Data Index: 3795009 (Open Web Text)

Max Activating Token Index: 9

Text #11

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4534. Min Act: -0.1700

Data Index: 366710 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4465. Min Act: -0.1695

Data Index: 8316035 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4575. Min Act: -0.1696

Data Index: 177596 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4485. Min Act: -0.1680

Data Index: 2387687 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4156. Min Act: -0.1700

Data Index: 505311 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4147. Min Act: -0.1637

Data Index: 6314967 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4095. Min Act: -0.1700

Data Index: 6671394 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4076. Min Act: -0.1646

Data Index: 6996689 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 1.5482. Min Range: -1.5482

Max Act: 1.4083. Min Act: -0.1643

Data Index: 2848961 (Open Web Text)

Max Activating Token Index: 34