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

Dataset: Open Web Text

Neuron 2763 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: 3.1310. Min Range: -3.1310

Max Act: 3.1310. Min Act: -0.1700

Data Index: 2113248 (Open Web Text)

Max Activating Token Index: 223

Text #1

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.9871. Min Act: -0.1700

Data Index: 5600314 (Open Web Text)

Max Activating Token Index: 26

Text #2

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.9402. Min Act: -0.1700

Data Index: 6348158 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.9082. Min Act: -0.1700

Data Index: 3820417 (Open Web Text)

Max Activating Token Index: 20

Text #4

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.9069. Min Act: -0.1700

Data Index: 2841163 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.8896. Min Act: -0.1700

Data Index: 1064656 (Open Web Text)

Max Activating Token Index: 1007

Text #6

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.8934. Min Act: -0.1700

Data Index: 3060501 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.9064. Min Act: -0.1700

Data Index: 7098246 (Open Web Text)

Max Activating Token Index: 635

Text #8

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.8914. Min Act: -0.1700

Data Index: 130430 (Open Web Text)

Max Activating Token Index: 52

Text #9

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.8818. Min Act: -0.1700

Data Index: 6067388 (Open Web Text)

Max Activating Token Index: 26

Text #10

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.8817. Min Act: -0.1700

Data Index: 7680293 (Open Web Text)

Max Activating Token Index: 637

Text #11

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.8793. Min Act: -0.1700

Data Index: 137357 (Open Web Text)

Max Activating Token Index: 688

Text #12

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.8858. Min Act: -0.1700

Data Index: 4161384 (Open Web Text)

Max Activating Token Index: 759

Text #13

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.8724. Min Act: -0.1700

Data Index: 1457389 (Open Web Text)

Max Activating Token Index: 23

Text #14

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.8778. Min Act: -0.1700

Data Index: 7526766 (Open Web Text)

Max Activating Token Index: 646

Text #15

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.8527. Min Act: -0.1700

Data Index: 8681238 (Open Web Text)

Max Activating Token Index: 86

Text #16

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.8613. Min Act: -0.1700

Data Index: 6535470 (Open Web Text)

Max Activating Token Index: 656

Text #17

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.8637. Min Act: -0.1700

Data Index: 6938655 (Open Web Text)

Max Activating Token Index: 677

Text #18

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.8642. Min Act: -0.1700

Data Index: 5812294 (Open Web Text)

Max Activating Token Index: 532

Text #19

Max Range: 3.1310. Min Range: -3.1310

Max Act: 2.8588. Min Act: -0.1700

Data Index: 3833983 (Open Web Text)

Max Activating Token Index: 105