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

Dataset: Open Web Text

Neuron 589 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: 3.4802. Min Range: -3.4802

Max Act: 3.4802. Min Act: -0.1700

Data Index: 7453673 (Open Web Text)

Max Activating Token Index: 277

Text #1

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.3840. Min Act: -0.1700

Data Index: 6895287 (Open Web Text)

Max Activating Token Index: 386

Text #2

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.3435. Min Act: -0.1700

Data Index: 4807366 (Open Web Text)

Max Activating Token Index: 439

Text #3

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.3533. Min Act: -0.1700

Data Index: 657592 (Open Web Text)

Max Activating Token Index: 540

Text #4

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.3006. Min Act: -0.1700

Data Index: 2170636 (Open Web Text)

Max Activating Token Index: 311

Text #5

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.2581. Min Act: -0.1700

Data Index: 601451 (Open Web Text)

Max Activating Token Index: 577

Text #6

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.2744. Min Act: -0.1700

Data Index: 876950 (Open Web Text)

Max Activating Token Index: 624

Text #7

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.2785. Min Act: -0.1700

Data Index: 1404603 (Open Web Text)

Max Activating Token Index: 978

Text #8

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.2552. Min Act: -0.1700

Data Index: 7532225 (Open Web Text)

Max Activating Token Index: 172

Text #9

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.2888. Min Act: -0.1700

Data Index: 5721360 (Open Web Text)

Max Activating Token Index: 235

Text #10

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.2729. Min Act: -0.1700

Data Index: 5856455 (Open Web Text)

Max Activating Token Index: 706

Text #11

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.2839. Min Act: -0.1700

Data Index: 5796101 (Open Web Text)

Max Activating Token Index: 1008

Text #12

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.2544. Min Act: -0.1700

Data Index: 4890424 (Open Web Text)

Max Activating Token Index: 543

Text #13

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.2622. Min Act: -0.1700

Data Index: 7597535 (Open Web Text)

Max Activating Token Index: 769

Text #14

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.2066. Min Act: -0.1700

Data Index: 7689579 (Open Web Text)

Max Activating Token Index: 449

Text #15

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.2373. Min Act: -0.1700

Data Index: 8780522 (Open Web Text)

Max Activating Token Index: 105

Text #16

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.2410. Min Act: -0.1700

Data Index: 6089686 (Open Web Text)

Max Activating Token Index: 134

Text #17

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.2595. Min Act: -0.1700

Data Index: 809745 (Open Web Text)

Max Activating Token Index: 480

Text #18

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.2084. Min Act: -0.1700

Data Index: 3102887 (Open Web Text)

Max Activating Token Index: 388

Text #19

Max Range: 3.4802. Min Range: -3.4802

Max Act: 3.2366. Min Act: -0.1700

Data Index: 5621004 (Open Web Text)

Max Activating Token Index: 495