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

Dataset: Open Web Text

Neuron 1809 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: 3.8680. Min Range: -3.8680

Max Act: 3.8680. Min Act: -0.1700

Data Index: 235971 (Open Web Text)

Max Activating Token Index: 358

Text #1

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.8434. Min Act: -0.1700

Data Index: 2142937 (Open Web Text)

Max Activating Token Index: 589

Text #2

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.8269. Min Act: -0.1700

Data Index: 8526078 (Open Web Text)

Max Activating Token Index: 373

Text #3

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.8092. Min Act: -0.1700

Data Index: 8568461 (Open Web Text)

Max Activating Token Index: 595

Text #4

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.8058. Min Act: -0.1700

Data Index: 6515188 (Open Web Text)

Max Activating Token Index: 200

Text #5

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.7849. Min Act: -0.1700

Data Index: 2304505 (Open Web Text)

Max Activating Token Index: 90

Text #6

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.7992. Min Act: -0.1700

Data Index: 378072 (Open Web Text)

Max Activating Token Index: 176

Text #7

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.7880. Min Act: -0.1700

Data Index: 1002216 (Open Web Text)

Max Activating Token Index: 84

Text #8

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.7740. Min Act: -0.1700

Data Index: 5325999 (Open Web Text)

Max Activating Token Index: 431

Text #9

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.7645. Min Act: -0.1700

Data Index: 8298862 (Open Web Text)

Max Activating Token Index: 543

Text #10

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.7803. Min Act: -0.1700

Data Index: 8073807 (Open Web Text)

Max Activating Token Index: 70

Text #11

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.7599. Min Act: -0.1700

Data Index: 4502797 (Open Web Text)

Max Activating Token Index: 814

Text #12

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.7608. Min Act: -0.1700

Data Index: 3791224 (Open Web Text)

Max Activating Token Index: 485

Text #13

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.7675. Min Act: -0.1700

Data Index: 1305454 (Open Web Text)

Max Activating Token Index: 158

Text #14

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.7642. Min Act: -0.1700

Data Index: 6250363 (Open Web Text)

Max Activating Token Index: 924

Text #15

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.7817. Min Act: -0.1700

Data Index: 389103 (Open Web Text)

Max Activating Token Index: 433

Text #16

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.7257. Min Act: -0.1700

Data Index: 2956728 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.7568. Min Act: -0.1700

Data Index: 1560188 (Open Web Text)

Max Activating Token Index: 378

Text #18

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.7387. Min Act: -0.1700

Data Index: 270598 (Open Web Text)

Max Activating Token Index: 107

Text #19

Max Range: 3.8680. Min Range: -3.8680

Max Act: 3.7236. Min Act: -0.1700

Data Index: 6405839 (Open Web Text)

Max Activating Token Index: 875