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

Dataset: Open Web Text

Neuron 808 in Layer 3

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: 3.7534. Min Range: -3.7534

Max Act: 3.7534. Min Act: -0.1700

Data Index: 7448439 (Open Web Text)

Max Activating Token Index: 933

Text #1

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.7202. Min Act: -0.1700

Data Index: 2929345 (Open Web Text)

Max Activating Token Index: 775

Text #2

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.7335. Min Act: -0.1700

Data Index: 4144466 (Open Web Text)

Max Activating Token Index: 100

Text #3

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6840. Min Act: -0.1700

Data Index: 4533489 (Open Web Text)

Max Activating Token Index: 22

Text #4

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6888. Min Act: -0.1700

Data Index: 4626895 (Open Web Text)

Max Activating Token Index: 43

Text #5

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6981. Min Act: -0.1700

Data Index: 8098200 (Open Web Text)

Max Activating Token Index: 512

Text #6

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.7083. Min Act: -0.1700

Data Index: 6222694 (Open Web Text)

Max Activating Token Index: 263

Text #7

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.7098. Min Act: -0.1700

Data Index: 7580510 (Open Web Text)

Max Activating Token Index: 557

Text #8

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6774. Min Act: -0.1700

Data Index: 2902095 (Open Web Text)

Max Activating Token Index: 437

Text #9

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6241. Min Act: -0.1700

Data Index: 3412362 (Open Web Text)

Max Activating Token Index: 990

Text #10

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6947. Min Act: -0.1700

Data Index: 8017281 (Open Web Text)

Max Activating Token Index: 524

Text #11

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6790. Min Act: -0.1700

Data Index: 7450569 (Open Web Text)

Max Activating Token Index: 689

Text #12

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6535. Min Act: -0.1700

Data Index: 3981970 (Open Web Text)

Max Activating Token Index: 469

Text #13

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6912. Min Act: -0.1700

Data Index: 7154953 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6590. Min Act: -0.1700

Data Index: 6691459 (Open Web Text)

Max Activating Token Index: 234

Text #15

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6477. Min Act: -0.1700

Data Index: 6360069 (Open Web Text)

Max Activating Token Index: 596

Text #16

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6552. Min Act: -0.1700

Data Index: 3069798 (Open Web Text)

Max Activating Token Index: 372

Text #17

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6568. Min Act: -0.1700

Data Index: 2415666 (Open Web Text)

Max Activating Token Index: 347

Text #18

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6528. Min Act: -0.1700

Data Index: 2876665 (Open Web Text)

Max Activating Token Index: 550

Text #19

Max Range: 3.7534. Min Range: -3.7534

Max Act: 3.6600. Min Act: -0.1700

Data Index: 601420 (Open Web Text)

Max Activating Token Index: 804