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

Dataset: Open Web Text

Neuron 2920 in Layer 5

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: 3.5293. Min Range: -3.5293

Max Act: 3.5293. Min Act: -0.1700

Data Index: 6371107 (Open Web Text)

Max Activating Token Index: 142

Text #1

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.4494. Min Act: -0.1700

Data Index: 5286583 (Open Web Text)

Max Activating Token Index: 363

Text #2

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.4668. Min Act: -0.1700

Data Index: 8442366 (Open Web Text)

Max Activating Token Index: 981

Text #3

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.4666. Min Act: -0.1700

Data Index: 8159844 (Open Web Text)

Max Activating Token Index: 320

Text #4

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.4285. Min Act: -0.1700

Data Index: 5270003 (Open Web Text)

Max Activating Token Index: 1005

Text #5

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.4076. Min Act: -0.1700

Data Index: 7279045 (Open Web Text)

Max Activating Token Index: 762

Text #6

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.3816. Min Act: -0.1700

Data Index: 7893556 (Open Web Text)

Max Activating Token Index: 77

Text #7

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.3181. Min Act: -0.1700

Data Index: 152062 (Open Web Text)

Max Activating Token Index: 989

Text #8

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.2781. Min Act: -0.1700

Data Index: 7630079 (Open Web Text)

Max Activating Token Index: 579

Text #9

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.2540. Min Act: -0.1700

Data Index: 5493477 (Open Web Text)

Max Activating Token Index: 609

Text #10

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.3429. Min Act: -0.1700

Data Index: 1946733 (Open Web Text)

Max Activating Token Index: 786

Text #11

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.2403. Min Act: -0.1700

Data Index: 5013025 (Open Web Text)

Max Activating Token Index: 426

Text #12

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.2030. Min Act: -0.1700

Data Index: 4861924 (Open Web Text)

Max Activating Token Index: 967

Text #13

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.2033. Min Act: -0.1700

Data Index: 5412762 (Open Web Text)

Max Activating Token Index: 110

Text #14

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.2402. Min Act: -0.1700

Data Index: 659756 (Open Web Text)

Max Activating Token Index: 324

Text #15

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.1651. Min Act: -0.1700

Data Index: 5991439 (Open Web Text)

Max Activating Token Index: 111

Text #16

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.1786. Min Act: -0.1700

Data Index: 3451300 (Open Web Text)

Max Activating Token Index: 271

Text #17

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.1490. Min Act: -0.1700

Data Index: 5548323 (Open Web Text)

Max Activating Token Index: 128

Text #18

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.1752. Min Act: -0.1700

Data Index: 3030193 (Open Web Text)

Max Activating Token Index: 871

Text #19

Max Range: 3.5293. Min Range: -3.5293

Max Act: 3.1149. Min Act: -0.1700

Data Index: 6368595 (Open Web Text)

Max Activating Token Index: 624