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

Dataset: Open Web Text

Neuron 1642 in Layer 6

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: 3.8538. Min Range: -3.8538

Max Act: 3.8538. Min Act: -0.1700

Data Index: 209357 (Open Web Text)

Max Activating Token Index: 593

Text #1

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.8024. Min Act: -0.1700

Data Index: 1374034 (Open Web Text)

Max Activating Token Index: 1014

Text #2

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7687. Min Act: -0.1700

Data Index: 7955307 (Open Web Text)

Max Activating Token Index: 1020

Text #3

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7748. Min Act: -0.1700

Data Index: 4485006 (Open Web Text)

Max Activating Token Index: 637

Text #4

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7619. Min Act: -0.1700

Data Index: 2828229 (Open Web Text)

Max Activating Token Index: 222

Text #5

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7268. Min Act: -0.1700

Data Index: 2144127 (Open Web Text)

Max Activating Token Index: 305

Text #6

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7352. Min Act: -0.1700

Data Index: 6383107 (Open Web Text)

Max Activating Token Index: 523

Text #7

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7472. Min Act: -0.1700

Data Index: 6570332 (Open Web Text)

Max Activating Token Index: 903

Text #8

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7406. Min Act: -0.1700

Data Index: 6945986 (Open Web Text)

Max Activating Token Index: 164

Text #9

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7284. Min Act: -0.1700

Data Index: 4160774 (Open Web Text)

Max Activating Token Index: 169

Text #10

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7277. Min Act: -0.1700

Data Index: 6721971 (Open Web Text)

Max Activating Token Index: 829

Text #11

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7282. Min Act: -0.1700

Data Index: 2009425 (Open Web Text)

Max Activating Token Index: 310

Text #12

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7188. Min Act: -0.1700

Data Index: 836918 (Open Web Text)

Max Activating Token Index: 1021

Text #13

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.6817. Min Act: -0.1700

Data Index: 4365614 (Open Web Text)

Max Activating Token Index: 809

Text #14

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7162. Min Act: -0.1700

Data Index: 7804975 (Open Web Text)

Max Activating Token Index: 326

Text #15

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7083. Min Act: -0.1700

Data Index: 4228365 (Open Web Text)

Max Activating Token Index: 130

Text #16

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.7083. Min Act: -0.1700

Data Index: 2856456 (Open Web Text)

Max Activating Token Index: 947

Text #17

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.6971. Min Act: -0.1700

Data Index: 3030165 (Open Web Text)

Max Activating Token Index: 644

Text #18

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.6876. Min Act: -0.1700

Data Index: 7689525 (Open Web Text)

Max Activating Token Index: 955

Text #19

Max Range: 3.8538. Min Range: -3.8538

Max Act: 3.6927. Min Act: -0.1700

Data Index: 63821 (Open Web Text)

Max Activating Token Index: 621