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

Dataset: Open Web Text

Neuron 1088 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: 7.5516. Min Range: -7.5516

Max Act: 7.5516. Min Act: -0.1700

Data Index: 421820 (Open Web Text)

Max Activating Token Index: 531

Text #1

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.4483. Min Act: -0.1700

Data Index: 8154269 (Open Web Text)

Max Activating Token Index: 363

Text #2

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.4218. Min Act: -0.1700

Data Index: 5320368 (Open Web Text)

Max Activating Token Index: 866

Text #3

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.3813. Min Act: -0.1700

Data Index: 6098274 (Open Web Text)

Max Activating Token Index: 717

Text #4

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.3461. Min Act: -0.1700

Data Index: 7005099 (Open Web Text)

Max Activating Token Index: 969

Text #5

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.3783. Min Act: -0.1700

Data Index: 126470 (Open Web Text)

Max Activating Token Index: 794

Text #6

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.2888. Min Act: -0.1700

Data Index: 1260070 (Open Web Text)

Max Activating Token Index: 653

Text #7

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.2173. Min Act: -0.1700

Data Index: 3158403 (Open Web Text)

Max Activating Token Index: 768

Text #8

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.2343. Min Act: -0.1700

Data Index: 7306783 (Open Web Text)

Max Activating Token Index: 656

Text #9

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.2839. Min Act: -0.1700

Data Index: 3083967 (Open Web Text)

Max Activating Token Index: 410

Text #10

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.2642. Min Act: -0.1700

Data Index: 7183072 (Open Web Text)

Max Activating Token Index: 871

Text #11

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.2153. Min Act: -0.1700

Data Index: 3290536 (Open Web Text)

Max Activating Token Index: 741

Text #12

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.2168. Min Act: -0.1700

Data Index: 4198094 (Open Web Text)

Max Activating Token Index: 446

Text #13

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.2465. Min Act: -0.1700

Data Index: 787352 (Open Web Text)

Max Activating Token Index: 712

Text #14

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.2157. Min Act: -0.1700

Data Index: 2182862 (Open Web Text)

Max Activating Token Index: 776

Text #15

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.1291. Min Act: -0.1700

Data Index: 681797 (Open Web Text)

Max Activating Token Index: 792

Text #16

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.1490. Min Act: -0.1700

Data Index: 4064998 (Open Web Text)

Max Activating Token Index: 640

Text #17

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.1876. Min Act: -0.1700

Data Index: 1110953 (Open Web Text)

Max Activating Token Index: 540

Text #18

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.1538. Min Act: -0.1700

Data Index: 2729134 (Open Web Text)

Max Activating Token Index: 506

Text #19

Max Range: 7.5516. Min Range: -7.5516

Max Act: 7.1402. Min Act: -0.1700

Data Index: 5978767 (Open Web Text)

Max Activating Token Index: 857