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

Dataset: Open Web Text

Neuron 1528 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: 4.9774. Min Range: -4.9774

Max Act: 4.9774. Min Act: -0.1700

Data Index: 7693868 (Open Web Text)

Max Activating Token Index: 498

Text #1

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.9687. Min Act: -0.1700

Data Index: 7769657 (Open Web Text)

Max Activating Token Index: 547

Text #2

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.9455. Min Act: -0.1700

Data Index: 5163076 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.9222. Min Act: -0.1700

Data Index: 4385430 (Open Web Text)

Max Activating Token Index: 774

Text #4

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.9115. Min Act: -0.1700

Data Index: 8750660 (Open Web Text)

Max Activating Token Index: 487

Text #5

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.8957. Min Act: -0.1700

Data Index: 5705971 (Open Web Text)

Max Activating Token Index: 483

Text #6

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.8557. Min Act: -0.1700

Data Index: 1342854 (Open Web Text)

Max Activating Token Index: 642

Text #7

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.8545. Min Act: -0.1700

Data Index: 8647673 (Open Web Text)

Max Activating Token Index: 133

Text #8

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.8568. Min Act: -0.1700

Data Index: 910201 (Open Web Text)

Max Activating Token Index: 486

Text #9

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.8689. Min Act: -0.1700

Data Index: 1450841 (Open Web Text)

Max Activating Token Index: 719

Text #10

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.8759. Min Act: -0.1700

Data Index: 8819144 (Open Web Text)

Max Activating Token Index: 442

Text #11

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.8558. Min Act: -0.1700

Data Index: 8724978 (Open Web Text)

Max Activating Token Index: 279

Text #12

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.8594. Min Act: -0.1700

Data Index: 6509972 (Open Web Text)

Max Activating Token Index: 205

Text #13

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.8420. Min Act: -0.1700

Data Index: 2755430 (Open Web Text)

Max Activating Token Index: 933

Text #14

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.8353. Min Act: -0.1700

Data Index: 2212667 (Open Web Text)

Max Activating Token Index: 145

Text #15

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.8308. Min Act: -0.1700

Data Index: 3075482 (Open Web Text)

Max Activating Token Index: 143

Text #16

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.8584. Min Act: -0.1700

Data Index: 8285574 (Open Web Text)

Max Activating Token Index: 158

Text #17

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.8317. Min Act: -0.1700

Data Index: 8482600 (Open Web Text)

Max Activating Token Index: 380

Text #18

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.8394. Min Act: -0.1700

Data Index: 2513233 (Open Web Text)

Max Activating Token Index: 104

Text #19

Max Range: 4.9774. Min Range: -4.9774

Max Act: 4.8298. Min Act: -0.1700

Data Index: 6330040 (Open Web Text)

Max Activating Token Index: 492