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

Dataset: Open Web Text

Neuron 674 in Layer 2

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: 4.5077. Min Range: -4.5077

Max Act: 4.4753. Min Act: -0.1700

Data Index: 2095900 (Open Web Text)

Max Activating Token Index: 42

Text #1

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.4802. Min Act: -0.1700

Data Index: 5956613 (Open Web Text)

Max Activating Token Index: 241

Text #2

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.5077. Min Act: -0.1700

Data Index: 2256984 (Open Web Text)

Max Activating Token Index: 682

Text #3

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.4547. Min Act: -0.1700

Data Index: 8438294 (Open Web Text)

Max Activating Token Index: 944

Text #4

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.4195. Min Act: -0.1700

Data Index: 2680071 (Open Web Text)

Max Activating Token Index: 299

Text #5

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.4201. Min Act: -0.1700

Data Index: 43893 (Open Web Text)

Max Activating Token Index: 309

Text #6

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.3513. Min Act: -0.1700

Data Index: 141247 (Open Web Text)

Max Activating Token Index: 22

Text #7

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.3446. Min Act: -0.1700

Data Index: 1891123 (Open Web Text)

Max Activating Token Index: 825

Text #8

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.3259. Min Act: -0.1700

Data Index: 3176340 (Open Web Text)

Max Activating Token Index: 784

Text #9

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.2902. Min Act: -0.1700

Data Index: 3993289 (Open Web Text)

Max Activating Token Index: 269

Text #10

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.3031. Min Act: -0.1700

Data Index: 3111029 (Open Web Text)

Max Activating Token Index: 101

Text #11

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.2979. Min Act: -0.1700

Data Index: 2219987 (Open Web Text)

Max Activating Token Index: 494

Text #12

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.2637. Min Act: -0.1700

Data Index: 140392 (Open Web Text)

Max Activating Token Index: 541

Text #13

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.2643. Min Act: -0.1700

Data Index: 1344031 (Open Web Text)

Max Activating Token Index: 264

Text #14

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.2548. Min Act: -0.1700

Data Index: 5262676 (Open Web Text)

Max Activating Token Index: 399

Text #15

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.2628. Min Act: -0.1700

Data Index: 7517331 (Open Web Text)

Max Activating Token Index: 965

Text #16

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.2224. Min Act: -0.1700

Data Index: 3608450 (Open Web Text)

Max Activating Token Index: 984

Text #17

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.2194. Min Act: -0.1700

Data Index: 4830697 (Open Web Text)

Max Activating Token Index: 620

Text #18

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.2189. Min Act: -0.1700

Data Index: 345318 (Open Web Text)

Max Activating Token Index: 515

Text #19

Max Range: 4.5077. Min Range: -4.5077

Max Act: 4.2376. Min Act: -0.1700

Data Index: 3661337 (Open Web Text)

Max Activating Token Index: 380