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

Dataset: Open Web Text

Neuron 2254 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: 4.2009. Min Range: -4.2009

Max Act: 4.2009. Min Act: -0.1700

Data Index: 7285921 (Open Web Text)

Max Activating Token Index: 44

Text #1

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.1280. Min Act: -0.1700

Data Index: 3253123 (Open Web Text)

Max Activating Token Index: 193

Text #2

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.1349. Min Act: -0.1700

Data Index: 8069638 (Open Web Text)

Max Activating Token Index: 96

Text #3

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.1305. Min Act: -0.1700

Data Index: 4936665 (Open Web Text)

Max Activating Token Index: 155

Text #4

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.1018. Min Act: -0.1700

Data Index: 4015837 (Open Web Text)

Max Activating Token Index: 67

Text #5

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.1212. Min Act: -0.1700

Data Index: 5142643 (Open Web Text)

Max Activating Token Index: 438

Text #6

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.1071. Min Act: -0.1700

Data Index: 1475837 (Open Web Text)

Max Activating Token Index: 80

Text #7

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.0982. Min Act: -0.1700

Data Index: 4358017 (Open Web Text)

Max Activating Token Index: 189

Text #8

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.0680. Min Act: -0.1700

Data Index: 5856039 (Open Web Text)

Max Activating Token Index: 316

Text #9

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.0913. Min Act: -0.1700

Data Index: 2487338 (Open Web Text)

Max Activating Token Index: 98

Text #10

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.0810. Min Act: -0.1700

Data Index: 1654860 (Open Web Text)

Max Activating Token Index: 201

Text #11

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.0750. Min Act: -0.1700

Data Index: 5064476 (Open Web Text)

Max Activating Token Index: 23

Text #12

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.0426. Min Act: -0.1700

Data Index: 1098268 (Open Web Text)

Max Activating Token Index: 243

Text #13

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.0443. Min Act: -0.1700

Data Index: 8340648 (Open Web Text)

Max Activating Token Index: 227

Text #14

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.0689. Min Act: -0.1700

Data Index: 4658710 (Open Web Text)

Max Activating Token Index: 126

Text #15

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.0379. Min Act: -0.1700

Data Index: 7451147 (Open Web Text)

Max Activating Token Index: 464

Text #16

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.0671. Min Act: -0.1700

Data Index: 816055 (Open Web Text)

Max Activating Token Index: 403

Text #17

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.0473. Min Act: -0.1700

Data Index: 2254020 (Open Web Text)

Max Activating Token Index: 894

Text #18

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.0556. Min Act: -0.1700

Data Index: 5564609 (Open Web Text)

Max Activating Token Index: 550

Text #19

Max Range: 4.2009. Min Range: -4.2009

Max Act: 4.0320. Min Act: -0.1700

Data Index: 5352618 (Open Web Text)

Max Activating Token Index: 89