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

Dataset: Open Web Text

Neuron 1927 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: 2.3761. Min Range: -2.3761

Max Act: 2.3761. Min Act: -0.1700

Data Index: 2977639 (Open Web Text)

Max Activating Token Index: 538

Text #1

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.3509. Min Act: -0.1700

Data Index: 3220093 (Open Web Text)

Max Activating Token Index: 606

Text #2

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.3422. Min Act: -0.1700

Data Index: 6067859 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2971. Min Act: -0.1700

Data Index: 2251374 (Open Web Text)

Max Activating Token Index: 911

Text #4

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2874. Min Act: -0.1700

Data Index: 3169044 (Open Web Text)

Max Activating Token Index: 553

Text #5

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2865. Min Act: -0.1700

Data Index: 2062153 (Open Web Text)

Max Activating Token Index: 613

Text #6

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2762. Min Act: -0.1700

Data Index: 5565358 (Open Web Text)

Max Activating Token Index: 626

Text #7

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2843. Min Act: -0.1700

Data Index: 7080837 (Open Web Text)

Max Activating Token Index: 510

Text #8

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2903. Min Act: -0.1700

Data Index: 376013 (Open Web Text)

Max Activating Token Index: 476

Text #9

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2655. Min Act: -0.1700

Data Index: 3830279 (Open Web Text)

Max Activating Token Index: 109

Text #10

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2644. Min Act: -0.1700

Data Index: 6833797 (Open Web Text)

Max Activating Token Index: 458

Text #11

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2482. Min Act: -0.1700

Data Index: 7049137 (Open Web Text)

Max Activating Token Index: 774

Text #12

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2589. Min Act: -0.1700

Data Index: 3514606 (Open Web Text)

Max Activating Token Index: 481

Text #13

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2608. Min Act: -0.1700

Data Index: 6258034 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2429. Min Act: -0.1700

Data Index: 694829 (Open Web Text)

Max Activating Token Index: 265

Text #15

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2741. Min Act: -0.1700

Data Index: 642562 (Open Web Text)

Max Activating Token Index: 903

Text #16

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2278. Min Act: -0.1700

Data Index: 6433778 (Open Web Text)

Max Activating Token Index: 860

Text #17

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2605. Min Act: -0.1700

Data Index: 7362111 (Open Web Text)

Max Activating Token Index: 318

Text #18

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2645. Min Act: -0.1700

Data Index: 8053025 (Open Web Text)

Max Activating Token Index: 559

Text #19

Max Range: 2.3761. Min Range: -2.3761

Max Act: 2.2461. Min Act: -0.1700

Data Index: 2012953 (Open Web Text)

Max Activating Token Index: 9