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

Dataset: Open Web Text

Neuron 532 in Layer 4

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: 3.3367. Min Range: -3.3367

Max Act: 3.3229. Min Act: -0.1700

Data Index: 6554888 (Open Web Text)

Max Activating Token Index: 536

Text #1

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.3026. Min Act: -0.1700

Data Index: 2805316 (Open Web Text)

Max Activating Token Index: 442

Text #2

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.3367. Min Act: -0.1700

Data Index: 537904 (Open Web Text)

Max Activating Token Index: 338

Text #3

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.3053. Min Act: -0.1700

Data Index: 3732664 (Open Web Text)

Max Activating Token Index: 663

Text #4

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.2934. Min Act: -0.1700

Data Index: 8276476 (Open Web Text)

Max Activating Token Index: 579

Text #5

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.2672. Min Act: -0.1700

Data Index: 3307143 (Open Web Text)

Max Activating Token Index: 960

Text #6

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.2722. Min Act: -0.1700

Data Index: 6058171 (Open Web Text)

Max Activating Token Index: 644

Text #7

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.2665. Min Act: -0.1700

Data Index: 57869 (Open Web Text)

Max Activating Token Index: 631

Text #8

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.2184. Min Act: -0.1700

Data Index: 3766642 (Open Web Text)

Max Activating Token Index: 240

Text #9

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.2150. Min Act: -0.1700

Data Index: 1806541 (Open Web Text)

Max Activating Token Index: 320

Text #10

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.2104. Min Act: -0.1700

Data Index: 989013 (Open Web Text)

Max Activating Token Index: 996

Text #11

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.1889. Min Act: -0.1700

Data Index: 1107634 (Open Web Text)

Max Activating Token Index: 946

Text #12

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.1979. Min Act: -0.1700

Data Index: 7783477 (Open Web Text)

Max Activating Token Index: 533

Text #13

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.1940. Min Act: -0.1700

Data Index: 4973409 (Open Web Text)

Max Activating Token Index: 119

Text #14

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.1742. Min Act: -0.1700

Data Index: 7604180 (Open Web Text)

Max Activating Token Index: 963

Text #15

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.1811. Min Act: -0.1700

Data Index: 4258672 (Open Web Text)

Max Activating Token Index: 733

Text #16

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.1871. Min Act: -0.1700

Data Index: 3764055 (Open Web Text)

Max Activating Token Index: 797

Text #17

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.1686. Min Act: -0.1700

Data Index: 4890830 (Open Web Text)

Max Activating Token Index: 957

Text #18

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.1670. Min Act: -0.1700

Data Index: 492325 (Open Web Text)

Max Activating Token Index: 290

Text #19

Max Range: 3.3367. Min Range: -3.3367

Max Act: 3.1697. Min Act: -0.1700

Data Index: 1688857 (Open Web Text)

Max Activating Token Index: 129