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

Dataset: Open Web Text

Neuron 2916 in Layer 4

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: 3.8176. Min Range: -3.8176

Max Act: 3.8176. Min Act: -0.1700

Data Index: 1329489 (Open Web Text)

Max Activating Token Index: 323

Text #1

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7921. Min Act: -0.1700

Data Index: 8412829 (Open Web Text)

Max Activating Token Index: 165

Text #2

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7656. Min Act: -0.1700

Data Index: 437178 (Open Web Text)

Max Activating Token Index: 819

Text #3

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7777. Min Act: -0.1700

Data Index: 896970 (Open Web Text)

Max Activating Token Index: 600

Text #4

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7829. Min Act: -0.1700

Data Index: 7908437 (Open Web Text)

Max Activating Token Index: 299

Text #5

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7476. Min Act: -0.1700

Data Index: 2747515 (Open Web Text)

Max Activating Token Index: 1010

Text #6

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7208. Min Act: -0.1700

Data Index: 8270693 (Open Web Text)

Max Activating Token Index: 663

Text #7

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7298. Min Act: -0.1700

Data Index: 7243184 (Open Web Text)

Max Activating Token Index: 925

Text #8

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7147. Min Act: -0.1700

Data Index: 5595827 (Open Web Text)

Max Activating Token Index: 587

Text #9

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7067. Min Act: -0.1700

Data Index: 6571222 (Open Web Text)

Max Activating Token Index: 514

Text #10

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7035. Min Act: -0.1700

Data Index: 6870851 (Open Web Text)

Max Activating Token Index: 567

Text #11

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.7125. Min Act: -0.1700

Data Index: 1079648 (Open Web Text)

Max Activating Token Index: 932

Text #12

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6863. Min Act: -0.1700

Data Index: 1843119 (Open Web Text)

Max Activating Token Index: 462

Text #13

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6820. Min Act: -0.1700

Data Index: 1261406 (Open Web Text)

Max Activating Token Index: 710

Text #14

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6804. Min Act: -0.1700

Data Index: 6565850 (Open Web Text)

Max Activating Token Index: 787

Text #15

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6847. Min Act: -0.1700

Data Index: 6382104 (Open Web Text)

Max Activating Token Index: 837

Text #16

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6815. Min Act: -0.1700

Data Index: 2568852 (Open Web Text)

Max Activating Token Index: 961

Text #17

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6664. Min Act: -0.1700

Data Index: 4417671 (Open Web Text)

Max Activating Token Index: 297

Text #18

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6670. Min Act: -0.1700

Data Index: 1805402 (Open Web Text)

Max Activating Token Index: 845

Text #19

Max Range: 3.8176. Min Range: -3.8176

Max Act: 3.6765. Min Act: -0.1700

Data Index: 2196491 (Open Web Text)

Max Activating Token Index: 775