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

Dataset: Open Web Text

Neuron 2185 in Layer 0

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: 1.6916. Min Range: -1.6916

Max Act: 1.6916. Min Act: -0.1700

Data Index: 8087434 (Open Web Text)

Max Activating Token Index: 125

Text #1

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6836. Min Act: -0.1697

Data Index: 6243953 (Open Web Text)

Max Activating Token Index: 380

Text #2

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6877. Min Act: -0.1699

Data Index: 8200608 (Open Web Text)

Max Activating Token Index: 145

Text #3

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6817. Min Act: -0.1699

Data Index: 7975508 (Open Web Text)

Max Activating Token Index: 580

Text #4

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6652. Min Act: -0.1700

Data Index: 2859259 (Open Web Text)

Max Activating Token Index: 173

Text #5

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6680. Min Act: -0.1684

Data Index: 2101113 (Open Web Text)

Max Activating Token Index: 617

Text #6

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6614. Min Act: -0.1687

Data Index: 2775094 (Open Web Text)

Max Activating Token Index: 157

Text #7

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6549. Min Act: -0.1696

Data Index: 7671526 (Open Web Text)

Max Activating Token Index: 559

Text #8

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6470. Min Act: -0.1700

Data Index: 8636558 (Open Web Text)

Max Activating Token Index: 198

Text #9

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6513. Min Act: -0.1675

Data Index: 4020606 (Open Web Text)

Max Activating Token Index: 363

Text #10

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6454. Min Act: -0.1687

Data Index: 700151 (Open Web Text)

Max Activating Token Index: 97

Text #11

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6464. Min Act: -0.1700

Data Index: 7395635 (Open Web Text)

Max Activating Token Index: 346

Text #12

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6427. Min Act: -0.1657

Data Index: 4103064 (Open Web Text)

Max Activating Token Index: 196

Text #13

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6353. Min Act: -0.1585

Data Index: 7656413 (Open Web Text)

Max Activating Token Index: 1007

Text #14

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6400. Min Act: -0.1700

Data Index: 6006071 (Open Web Text)

Max Activating Token Index: 126

Text #15

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6291. Min Act: -0.1695

Data Index: 406244 (Open Web Text)

Max Activating Token Index: 226

Text #16

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6362. Min Act: -0.1700

Data Index: 5054357 (Open Web Text)

Max Activating Token Index: 1015

Text #17

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6313. Min Act: -0.1700

Data Index: 390256 (Open Web Text)

Max Activating Token Index: 84

Text #18

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6248. Min Act: -0.1699

Data Index: 7142161 (Open Web Text)

Max Activating Token Index: 367

Text #19

Max Range: 1.6916. Min Range: -1.6916

Max Act: 1.6285. Min Act: -0.1697

Data Index: 2430114 (Open Web Text)

Max Activating Token Index: 680