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

Dataset: Open Web Text

Neuron 521 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: 4.3736. Min Range: -4.3736

Max Act: 4.3736. Min Act: -0.1700

Data Index: 4017306 (Open Web Text)

Max Activating Token Index: 621

Text #1

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.3633. Min Act: -0.1700

Data Index: 1083052 (Open Web Text)

Max Activating Token Index: 803

Text #2

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.3629. Min Act: -0.1700

Data Index: 3641512 (Open Web Text)

Max Activating Token Index: 69

Text #3

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.3477. Min Act: -0.1700

Data Index: 6996625 (Open Web Text)

Max Activating Token Index: 726

Text #4

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.3487. Min Act: -0.1700

Data Index: 7258711 (Open Web Text)

Max Activating Token Index: 113

Text #5

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.3471. Min Act: -0.1700

Data Index: 8384433 (Open Web Text)

Max Activating Token Index: 945

Text #6

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.3504. Min Act: -0.1700

Data Index: 1804448 (Open Web Text)

Max Activating Token Index: 123

Text #7

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.3407. Min Act: -0.1700

Data Index: 5220876 (Open Web Text)

Max Activating Token Index: 774

Text #8

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.3361. Min Act: -0.1700

Data Index: 216282 (Open Web Text)

Max Activating Token Index: 399

Text #9

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.3280. Min Act: -0.1700

Data Index: 5220880 (Open Web Text)

Max Activating Token Index: 395

Text #10

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.3244. Min Act: -0.1700

Data Index: 6588824 (Open Web Text)

Max Activating Token Index: 906

Text #11

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.2948. Min Act: -0.1700

Data Index: 5645732 (Open Web Text)

Max Activating Token Index: 841

Text #12

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.3192. Min Act: -0.1700

Data Index: 1362951 (Open Web Text)

Max Activating Token Index: 832

Text #13

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.3207. Min Act: -0.1700

Data Index: 1903397 (Open Web Text)

Max Activating Token Index: 308

Text #14

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.3151. Min Act: -0.1700

Data Index: 8721480 (Open Web Text)

Max Activating Token Index: 820

Text #15

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.2777. Min Act: -0.1700

Data Index: 4368715 (Open Web Text)

Max Activating Token Index: 442

Text #16

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.2833. Min Act: -0.1700

Data Index: 2262028 (Open Web Text)

Max Activating Token Index: 863

Text #17

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.2827. Min Act: -0.1700

Data Index: 4066250 (Open Web Text)

Max Activating Token Index: 867

Text #18

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.2943. Min Act: -0.1700

Data Index: 1951204 (Open Web Text)

Max Activating Token Index: 152

Text #19

Max Range: 4.3736. Min Range: -4.3736

Max Act: 4.2788. Min Act: -0.1700

Data Index: 3426453 (Open Web Text)

Max Activating Token Index: 388