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

Dataset: Open Web Text

Neuron 121 in Layer 3

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: 3.9317. Min Range: -3.9317

Max Act: 3.9317. Min Act: -0.1700

Data Index: 4711647 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.9257. Min Act: -0.1700

Data Index: 4894041 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.8542. Min Act: -0.1700

Data Index: 4081249 (Open Web Text)

Max Activating Token Index: 218

Text #3

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.8585. Min Act: -0.1700

Data Index: 7641225 (Open Web Text)

Max Activating Token Index: 587

Text #4

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.8246. Min Act: -0.1700

Data Index: 6420886 (Open Web Text)

Max Activating Token Index: 185

Text #5

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.8714. Min Act: -0.1700

Data Index: 1218904 (Open Web Text)

Max Activating Token Index: 466

Text #6

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.8234. Min Act: -0.1700

Data Index: 4310148 (Open Web Text)

Max Activating Token Index: 427

Text #7

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.8117. Min Act: -0.1700

Data Index: 7098186 (Open Web Text)

Max Activating Token Index: 732

Text #8

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.7903. Min Act: -0.1700

Data Index: 7625020 (Open Web Text)

Max Activating Token Index: 379

Text #9

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.8155. Min Act: -0.1700

Data Index: 958094 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.7675. Min Act: -0.1700

Data Index: 5599033 (Open Web Text)

Max Activating Token Index: 205

Text #11

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.7717. Min Act: -0.1700

Data Index: 4196968 (Open Web Text)

Max Activating Token Index: 339

Text #12

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.7914. Min Act: -0.1700

Data Index: 2901976 (Open Web Text)

Max Activating Token Index: 108

Text #13

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.7391. Min Act: -0.1700

Data Index: 5808242 (Open Web Text)

Max Activating Token Index: 463

Text #14

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.7349. Min Act: -0.1700

Data Index: 4619787 (Open Web Text)

Max Activating Token Index: 183

Text #15

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.7416. Min Act: -0.1700

Data Index: 7535354 (Open Web Text)

Max Activating Token Index: 459

Text #16

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.7127. Min Act: -0.1700

Data Index: 2171012 (Open Web Text)

Max Activating Token Index: 129

Text #17

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.7569. Min Act: -0.1700

Data Index: 5113814 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.7434. Min Act: -0.1700

Data Index: 5195612 (Open Web Text)

Max Activating Token Index: 48

Text #19

Max Range: 3.9317. Min Range: -3.9317

Max Act: 3.7022. Min Act: -0.1700

Data Index: 4894032 (Open Web Text)

Max Activating Token Index: 176