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

Dataset: Open Web Text

Neuron 1826 in Layer 2

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: 1.8541. Min Range: -1.8541

Max Act: 1.8420. Min Act: -0.1700

Data Index: 7795310 (Open Web Text)

Max Activating Token Index: 15

Text #1

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.8541. Min Act: -0.1700

Data Index: 6683742 (Open Web Text)

Max Activating Token Index: 1015

Text #2

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.8213. Min Act: -0.1700

Data Index: 2501195 (Open Web Text)

Max Activating Token Index: 932

Text #3

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.8278. Min Act: -0.1700

Data Index: 3681106 (Open Web Text)

Max Activating Token Index: 238

Text #4

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.8286. Min Act: -0.1700

Data Index: 6149457 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.8403. Min Act: -0.1700

Data Index: 1171114 (Open Web Text)

Max Activating Token Index: 232

Text #6

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.8324. Min Act: -0.1700

Data Index: 5792022 (Open Web Text)

Max Activating Token Index: 895

Text #7

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.8129. Min Act: -0.1700

Data Index: 308526 (Open Web Text)

Max Activating Token Index: 136

Text #8

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.8174. Min Act: -0.1700

Data Index: 8089909 (Open Web Text)

Max Activating Token Index: 872

Text #9

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7934. Min Act: -0.1700

Data Index: 6509370 (Open Web Text)

Max Activating Token Index: 392

Text #10

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7954. Min Act: -0.1700

Data Index: 2100194 (Open Web Text)

Max Activating Token Index: 601

Text #11

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7846. Min Act: -0.1700

Data Index: 1159810 (Open Web Text)

Max Activating Token Index: 603

Text #12

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7879. Min Act: -0.1700

Data Index: 2105504 (Open Web Text)

Max Activating Token Index: 641

Text #13

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7983. Min Act: -0.1700

Data Index: 359289 (Open Web Text)

Max Activating Token Index: 664

Text #14

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7891. Min Act: -0.1699

Data Index: 792226 (Open Web Text)

Max Activating Token Index: 407

Text #15

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7750. Min Act: -0.1700

Data Index: 1604624 (Open Web Text)

Max Activating Token Index: 168

Text #16

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7782. Min Act: -0.1700

Data Index: 4208833 (Open Web Text)

Max Activating Token Index: 395

Text #17

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7706. Min Act: -0.1700

Data Index: 816077 (Open Web Text)

Max Activating Token Index: 980

Text #18

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7669. Min Act: -0.1700

Data Index: 4295896 (Open Web Text)

Max Activating Token Index: 323

Text #19

Max Range: 1.8541. Min Range: -1.8541

Max Act: 1.7703. Min Act: -0.1700

Data Index: 354142 (Open Web Text)

Max Activating Token Index: 645