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

Dataset: Open Web Text

Neuron 217 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: 1.9550. Min Range: -1.9550

Max Act: 1.9550. Min Act: -0.1700

Data Index: 5918677 (Open Web Text)

Max Activating Token Index: 78

Text #1

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.9326. Min Act: -0.1700

Data Index: 1777767 (Open Web Text)

Max Activating Token Index: 212

Text #2

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.9066. Min Act: -0.1700

Data Index: 3736561 (Open Web Text)

Max Activating Token Index: 641

Text #3

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.9055. Min Act: -0.1700

Data Index: 7882798 (Open Web Text)

Max Activating Token Index: 158

Text #4

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.9015. Min Act: -0.1700

Data Index: 8054430 (Open Web Text)

Max Activating Token Index: 69

Text #5

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8995. Min Act: -0.1695

Data Index: 8446031 (Open Web Text)

Max Activating Token Index: 230

Text #6

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8888. Min Act: -0.1700

Data Index: 2385001 (Open Web Text)

Max Activating Token Index: 543

Text #7

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8830. Min Act: -0.1700

Data Index: 202698 (Open Web Text)

Max Activating Token Index: 354

Text #8

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8835. Min Act: -0.1700

Data Index: 74202 (Open Web Text)

Max Activating Token Index: 21

Text #9

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8906. Min Act: -0.1700

Data Index: 6564326 (Open Web Text)

Max Activating Token Index: 41

Text #10

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8760. Min Act: -0.1700

Data Index: 5563615 (Open Web Text)

Max Activating Token Index: 600

Text #11

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8662. Min Act: -0.1700

Data Index: 3056128 (Open Web Text)

Max Activating Token Index: 209

Text #12

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8631. Min Act: -0.1698

Data Index: 3541758 (Open Web Text)

Max Activating Token Index: 255

Text #13

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8592. Min Act: -0.1700

Data Index: 8044407 (Open Web Text)

Max Activating Token Index: 69

Text #14

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8663. Min Act: -0.1700

Data Index: 2117073 (Open Web Text)

Max Activating Token Index: 76

Text #15

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8676. Min Act: -0.1700

Data Index: 1095277 (Open Web Text)

Max Activating Token Index: 239

Text #16

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8530. Min Act: -0.1692

Data Index: 8653447 (Open Web Text)

Max Activating Token Index: 94

Text #17

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8408. Min Act: -0.1700

Data Index: 967198 (Open Web Text)

Max Activating Token Index: 763

Text #18

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8315. Min Act: -0.1700

Data Index: 1259746 (Open Web Text)

Max Activating Token Index: 835

Text #19

Max Range: 1.9550. Min Range: -1.9550

Max Act: 1.8323. Min Act: -0.1700

Data Index: 3056130 (Open Web Text)

Max Activating Token Index: 446