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

Dataset: Open Web Text

Neuron 666 in Layer 5

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: 4.7608. Min Range: -4.7608

Max Act: 4.7608. Min Act: -0.1700

Data Index: 7352145 (Open Web Text)

Max Activating Token Index: 989

Text #1

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.6565. Min Act: -0.1700

Data Index: 2755870 (Open Web Text)

Max Activating Token Index: 430

Text #2

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.6872. Min Act: -0.1700

Data Index: 6868182 (Open Web Text)

Max Activating Token Index: 721

Text #3

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.6361. Min Act: -0.1700

Data Index: 5912675 (Open Web Text)

Max Activating Token Index: 237

Text #4

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.6635. Min Act: -0.1700

Data Index: 3898079 (Open Web Text)

Max Activating Token Index: 570

Text #5

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.6875. Min Act: -0.1700

Data Index: 2387079 (Open Web Text)

Max Activating Token Index: 716

Text #6

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.6303. Min Act: -0.1700

Data Index: 6380177 (Open Web Text)

Max Activating Token Index: 1021

Text #7

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.6247. Min Act: -0.1700

Data Index: 6373761 (Open Web Text)

Max Activating Token Index: 153

Text #8

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.5981. Min Act: -0.1700

Data Index: 3155529 (Open Web Text)

Max Activating Token Index: 164

Text #9

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.6030. Min Act: -0.1700

Data Index: 4200824 (Open Web Text)

Max Activating Token Index: 421

Text #10

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.5915. Min Act: -0.1700

Data Index: 2595047 (Open Web Text)

Max Activating Token Index: 610

Text #11

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.6258. Min Act: -0.1700

Data Index: 1245984 (Open Web Text)

Max Activating Token Index: 474

Text #12

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.5924. Min Act: -0.1700

Data Index: 1986254 (Open Web Text)

Max Activating Token Index: 302

Text #13

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.5769. Min Act: -0.1700

Data Index: 2499464 (Open Web Text)

Max Activating Token Index: 440

Text #14

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.5622. Min Act: -0.1700

Data Index: 5147711 (Open Web Text)

Max Activating Token Index: 270

Text #15

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.5621. Min Act: -0.1700

Data Index: 6129476 (Open Web Text)

Max Activating Token Index: 122

Text #16

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.4944. Min Act: -0.1700

Data Index: 646227 (Open Web Text)

Max Activating Token Index: 717

Text #17

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.5257. Min Act: -0.1700

Data Index: 2367910 (Open Web Text)

Max Activating Token Index: 843

Text #18

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.4992. Min Act: -0.1700

Data Index: 1368723 (Open Web Text)

Max Activating Token Index: 344

Text #19

Max Range: 4.7608. Min Range: -4.7608

Max Act: 4.5448. Min Act: -0.1700

Data Index: 4089799 (Open Web Text)

Max Activating Token Index: 157