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

Dataset: Open Web Text

Neuron 1020 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: 1.8980. Min Range: -1.8980

Max Act: 1.8980. Min Act: -0.1700

Data Index: 3228680 (Open Web Text)

Max Activating Token Index: 389

Text #1

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.8013. Min Act: -0.1700

Data Index: 4635025 (Open Web Text)

Max Activating Token Index: 229

Text #2

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.8184. Min Act: -0.1699

Data Index: 6223376 (Open Web Text)

Max Activating Token Index: 252

Text #3

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.8167. Min Act: -0.1700

Data Index: 4978247 (Open Web Text)

Max Activating Token Index: 560

Text #4

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.8055. Min Act: -0.1700

Data Index: 5134050 (Open Web Text)

Max Activating Token Index: 456

Text #5

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7529. Min Act: -0.1700

Data Index: 628835 (Open Web Text)

Max Activating Token Index: 1015

Text #6

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7676. Min Act: -0.1700

Data Index: 5217366 (Open Web Text)

Max Activating Token Index: 277

Text #7

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7643. Min Act: -0.1700

Data Index: 8291550 (Open Web Text)

Max Activating Token Index: 19

Text #8

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7507. Min Act: -0.1700

Data Index: 8564503 (Open Web Text)

Max Activating Token Index: 531

Text #9

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7512. Min Act: -0.1700

Data Index: 2707658 (Open Web Text)

Max Activating Token Index: 75

Text #10

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7560. Min Act: -0.1700

Data Index: 4197166 (Open Web Text)

Max Activating Token Index: 246

Text #11

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7608. Min Act: -0.1700

Data Index: 5076904 (Open Web Text)

Max Activating Token Index: 503

Text #12

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7588. Min Act: -0.1700

Data Index: 7431183 (Open Web Text)

Max Activating Token Index: 952

Text #13

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7515. Min Act: -0.1696

Data Index: 3637144 (Open Web Text)

Max Activating Token Index: 28

Text #14

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7391. Min Act: -0.1700

Data Index: 6213371 (Open Web Text)

Max Activating Token Index: 566

Text #15

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7525. Min Act: -0.1700

Data Index: 3068514 (Open Web Text)

Max Activating Token Index: 659

Text #16

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7478. Min Act: -0.1700

Data Index: 3798419 (Open Web Text)

Max Activating Token Index: 277

Text #17

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7534. Min Act: -0.1700

Data Index: 558837 (Open Web Text)

Max Activating Token Index: 798

Text #18

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7544. Min Act: -0.1700

Data Index: 2213129 (Open Web Text)

Max Activating Token Index: 631

Text #19

Max Range: 1.8980. Min Range: -1.8980

Max Act: 1.7435. Min Act: -0.1700

Data Index: 3676975 (Open Web Text)

Max Activating Token Index: 375