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

Dataset: Open Web Text

Neuron 713 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: 4.0162. Min Range: -4.0162

Max Act: 4.0039. Min Act: -0.1700

Data Index: 3181867 (Open Web Text)

Max Activating Token Index: 322

Text #1

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.9692. Min Act: -0.1700

Data Index: 4514842 (Open Web Text)

Max Activating Token Index: 837

Text #2

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.9964. Min Act: -0.1700

Data Index: 1825363 (Open Web Text)

Max Activating Token Index: 400

Text #3

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.9886. Min Act: -0.1700

Data Index: 5146921 (Open Web Text)

Max Activating Token Index: 861

Text #4

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.9926. Min Act: -0.1700

Data Index: 1038281 (Open Web Text)

Max Activating Token Index: 605

Text #5

Max Range: 4.0162. Min Range: -4.0162

Max Act: 4.0162. Min Act: -0.1700

Data Index: 808473 (Open Web Text)

Max Activating Token Index: 795

Text #6

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.9764. Min Act: -0.1700

Data Index: 1451463 (Open Web Text)

Max Activating Token Index: 223

Text #7

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.9662. Min Act: -0.1700

Data Index: 1644546 (Open Web Text)

Max Activating Token Index: 645

Text #8

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.9651. Min Act: -0.1700

Data Index: 3153185 (Open Web Text)

Max Activating Token Index: 500

Text #9

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.9335. Min Act: -0.1700

Data Index: 8090718 (Open Web Text)

Max Activating Token Index: 20

Text #10

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.9638. Min Act: -0.1700

Data Index: 1216347 (Open Web Text)

Max Activating Token Index: 747

Text #11

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.9453. Min Act: -0.1700

Data Index: 3181445 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.9295. Min Act: -0.1700

Data Index: 6797701 (Open Web Text)

Max Activating Token Index: 17

Text #13

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.9322. Min Act: -0.1700

Data Index: 4951397 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.9536. Min Act: -0.1700

Data Index: 4653602 (Open Web Text)

Max Activating Token Index: 815

Text #15

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.9207. Min Act: -0.1700

Data Index: 6668675 (Open Web Text)

Max Activating Token Index: 343

Text #16

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.8974. Min Act: -0.1700

Data Index: 6482623 (Open Web Text)

Max Activating Token Index: 203

Text #17

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.8978. Min Act: -0.1700

Data Index: 1125662 (Open Web Text)

Max Activating Token Index: 849

Text #18

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.9124. Min Act: -0.1700

Data Index: 6143314 (Open Web Text)

Max Activating Token Index: 819

Text #19

Max Range: 4.0162. Min Range: -4.0162

Max Act: 3.8859. Min Act: -0.1700

Data Index: 3049381 (Open Web Text)

Max Activating Token Index: 461