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

Dataset: Open Web Text

Neuron 279 in Layer 6

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: 4.1351. Min Range: -4.1351

Max Act: 4.1351. Min Act: -0.1700

Data Index: 2791063 (Open Web Text)

Max Activating Token Index: 705

Text #1

Max Range: 4.1351. Min Range: -4.1351

Max Act: 4.0408. Min Act: -0.1700

Data Index: 5785690 (Open Web Text)

Max Activating Token Index: 639

Text #2

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.9724. Min Act: -0.1700

Data Index: 4942584 (Open Web Text)

Max Activating Token Index: 343

Text #3

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.9499. Min Act: -0.1700

Data Index: 8108138 (Open Web Text)

Max Activating Token Index: 313

Text #4

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.9052. Min Act: -0.1700

Data Index: 1297240 (Open Web Text)

Max Activating Token Index: 965

Text #5

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.9074. Min Act: -0.1700

Data Index: 5043689 (Open Web Text)

Max Activating Token Index: 269

Text #6

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.8400. Min Act: -0.1700

Data Index: 5197836 (Open Web Text)

Max Activating Token Index: 176

Text #7

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.8310. Min Act: -0.1700

Data Index: 1693107 (Open Web Text)

Max Activating Token Index: 93

Text #8

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.8127. Min Act: -0.1700

Data Index: 2984586 (Open Web Text)

Max Activating Token Index: 493

Text #9

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.8127. Min Act: -0.1700

Data Index: 6179420 (Open Web Text)

Max Activating Token Index: 703

Text #10

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.7675. Min Act: -0.1700

Data Index: 8482618 (Open Web Text)

Max Activating Token Index: 616

Text #11

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.7834. Min Act: -0.1700

Data Index: 3628321 (Open Web Text)

Max Activating Token Index: 927

Text #12

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.7616. Min Act: -0.1700

Data Index: 2753765 (Open Web Text)

Max Activating Token Index: 664

Text #13

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.8069. Min Act: -0.1700

Data Index: 1327440 (Open Web Text)

Max Activating Token Index: 458

Text #14

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.7697. Min Act: -0.1700

Data Index: 2619376 (Open Web Text)

Max Activating Token Index: 93

Text #15

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.7692. Min Act: -0.1700

Data Index: 5883505 (Open Web Text)

Max Activating Token Index: 736

Text #16

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.7841. Min Act: -0.1700

Data Index: 7926988 (Open Web Text)

Max Activating Token Index: 323

Text #17

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.7529. Min Act: -0.1700

Data Index: 2635505 (Open Web Text)

Max Activating Token Index: 309

Text #18

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.7559. Min Act: -0.1700

Data Index: 8451793 (Open Web Text)

Max Activating Token Index: 804

Text #19

Max Range: 4.1351. Min Range: -4.1351

Max Act: 3.7028. Min Act: -0.1700

Data Index: 5076752 (Open Web Text)

Max Activating Token Index: 356