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

Dataset: Open Web Text

Neuron 690 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: 5.8658. Min Range: -5.8658

Max Act: 5.8658. Min Act: -0.1700

Data Index: 300847 (Open Web Text)

Max Activating Token Index: 678

Text #1

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.8115. Min Act: -0.1700

Data Index: 5023326 (Open Web Text)

Max Activating Token Index: 692

Text #2

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7720. Min Act: -0.1700

Data Index: 2625768 (Open Web Text)

Max Activating Token Index: 517

Text #3

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7640. Min Act: -0.1700

Data Index: 2099056 (Open Web Text)

Max Activating Token Index: 637

Text #4

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7476. Min Act: -0.1700

Data Index: 4031166 (Open Web Text)

Max Activating Token Index: 313

Text #5

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7050. Min Act: -0.1700

Data Index: 6641322 (Open Web Text)

Max Activating Token Index: 115

Text #6

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.6755. Min Act: -0.1700

Data Index: 8084463 (Open Web Text)

Max Activating Token Index: 400

Text #7

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.6390. Min Act: -0.1700

Data Index: 1891636 (Open Web Text)

Max Activating Token Index: 873

Text #8

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.6803. Min Act: -0.1700

Data Index: 4646950 (Open Web Text)

Max Activating Token Index: 172

Text #9

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.6263. Min Act: -0.1700

Data Index: 3630054 (Open Web Text)

Max Activating Token Index: 206

Text #10

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.6080. Min Act: -0.1700

Data Index: 1422361 (Open Web Text)

Max Activating Token Index: 129

Text #11

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.6700. Min Act: -0.1700

Data Index: 8097078 (Open Web Text)

Max Activating Token Index: 203

Text #12

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.6437. Min Act: -0.1700

Data Index: 1385127 (Open Web Text)

Max Activating Token Index: 616

Text #13

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.6161. Min Act: -0.1700

Data Index: 45560 (Open Web Text)

Max Activating Token Index: 430

Text #14

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.6082. Min Act: -0.1700

Data Index: 1144252 (Open Web Text)

Max Activating Token Index: 513

Text #15

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.5867. Min Act: -0.1700

Data Index: 3628972 (Open Web Text)

Max Activating Token Index: 924

Text #16

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.5591. Min Act: -0.1700

Data Index: 821117 (Open Web Text)

Max Activating Token Index: 44

Text #17

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.5664. Min Act: -0.1700

Data Index: 4705612 (Open Web Text)

Max Activating Token Index: 163

Text #18

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.5908. Min Act: -0.1700

Data Index: 6807998 (Open Web Text)

Max Activating Token Index: 293

Text #19

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.5265. Min Act: -0.1700

Data Index: 3323467 (Open Web Text)

Max Activating Token Index: 639