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

Dataset: Open Web Text

Neuron 1843 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: 4.8322. Min Range: -4.8322

Max Act: 4.8322. Min Act: -0.1700

Data Index: 3692394 (Open Web Text)

Max Activating Token Index: 829

Text #1

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.7582. Min Act: -0.1700

Data Index: 3861492 (Open Web Text)

Max Activating Token Index: 362

Text #2

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.7215. Min Act: -0.1700

Data Index: 3534681 (Open Web Text)

Max Activating Token Index: 899

Text #3

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.6889. Min Act: -0.1700

Data Index: 6650841 (Open Web Text)

Max Activating Token Index: 567

Text #4

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.7022. Min Act: -0.1700

Data Index: 6772309 (Open Web Text)

Max Activating Token Index: 685

Text #5

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.6970. Min Act: -0.1700

Data Index: 628880 (Open Web Text)

Max Activating Token Index: 116

Text #6

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.7126. Min Act: -0.1700

Data Index: 5386918 (Open Web Text)

Max Activating Token Index: 690

Text #7

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.6831. Min Act: -0.1700

Data Index: 8269191 (Open Web Text)

Max Activating Token Index: 571

Text #8

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.6906. Min Act: -0.1700

Data Index: 5600533 (Open Web Text)

Max Activating Token Index: 330

Text #9

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.6594. Min Act: -0.1700

Data Index: 299380 (Open Web Text)

Max Activating Token Index: 224

Text #10

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.7005. Min Act: -0.1700

Data Index: 3409 (Open Web Text)

Max Activating Token Index: 758

Text #11

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.6551. Min Act: -0.1700

Data Index: 1613881 (Open Web Text)

Max Activating Token Index: 547

Text #12

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.6534. Min Act: -0.1700

Data Index: 1433684 (Open Web Text)

Max Activating Token Index: 37

Text #13

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.6491. Min Act: -0.1700

Data Index: 1377760 (Open Web Text)

Max Activating Token Index: 535

Text #14

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.6592. Min Act: -0.1700

Data Index: 3989763 (Open Web Text)

Max Activating Token Index: 589

Text #15

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.6297. Min Act: -0.1700

Data Index: 3088849 (Open Web Text)

Max Activating Token Index: 301

Text #16

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.6110. Min Act: -0.1700

Data Index: 5482251 (Open Web Text)

Max Activating Token Index: 520

Text #17

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.6579. Min Act: -0.1700

Data Index: 1916131 (Open Web Text)

Max Activating Token Index: 592

Text #18

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.6258. Min Act: -0.1700

Data Index: 1953484 (Open Web Text)

Max Activating Token Index: 410

Text #19

Max Range: 4.8322. Min Range: -4.8322

Max Act: 4.6474. Min Act: -0.1700

Data Index: 3301029 (Open Web Text)

Max Activating Token Index: 831