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

Dataset: Open Web Text

Neuron 1057 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: 3.7807. Min Range: -3.7807

Max Act: 3.7807. Min Act: -0.1700

Data Index: 3591185 (Open Web Text)

Max Activating Token Index: 666

Text #1

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5834. Min Act: -0.1700

Data Index: 4371849 (Open Web Text)

Max Activating Token Index: 894

Text #2

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5953. Min Act: -0.1700

Data Index: 1035063 (Open Web Text)

Max Activating Token Index: 620

Text #3

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5423. Min Act: -0.1700

Data Index: 658400 (Open Web Text)

Max Activating Token Index: 826

Text #4

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5632. Min Act: -0.1700

Data Index: 1141995 (Open Web Text)

Max Activating Token Index: 904

Text #5

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5709. Min Act: -0.1700

Data Index: 3101073 (Open Web Text)

Max Activating Token Index: 397

Text #6

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5347. Min Act: -0.1700

Data Index: 2364888 (Open Web Text)

Max Activating Token Index: 940

Text #7

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5162. Min Act: -0.1700

Data Index: 4552965 (Open Web Text)

Max Activating Token Index: 485

Text #8

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5248. Min Act: -0.1700

Data Index: 4934126 (Open Web Text)

Max Activating Token Index: 117

Text #9

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.4994. Min Act: -0.1700

Data Index: 2038252 (Open Web Text)

Max Activating Token Index: 982

Text #10

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5198. Min Act: -0.1700

Data Index: 8519701 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.4842. Min Act: -0.1700

Data Index: 4324694 (Open Web Text)

Max Activating Token Index: 22

Text #12

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.4636. Min Act: -0.1700

Data Index: 549058 (Open Web Text)

Max Activating Token Index: 26

Text #13

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.4719. Min Act: -0.1700

Data Index: 1081268 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.4394. Min Act: -0.1700

Data Index: 4825073 (Open Web Text)

Max Activating Token Index: 763

Text #15

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.4630. Min Act: -0.1700

Data Index: 4715704 (Open Web Text)

Max Activating Token Index: 330

Text #16

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.4538. Min Act: -0.1700

Data Index: 5887607 (Open Web Text)

Max Activating Token Index: 511

Text #17

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.5242. Min Act: -0.1700

Data Index: 670534 (Open Web Text)

Max Activating Token Index: 902

Text #18

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.4390. Min Act: -0.1700

Data Index: 6355695 (Open Web Text)

Max Activating Token Index: 587

Text #19

Max Range: 3.7807. Min Range: -3.7807

Max Act: 3.4293. Min Act: -0.1700

Data Index: 1195090 (Open Web Text)

Max Activating Token Index: 915