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

Dataset: Open Web Text

Neuron 1695 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: 4.4339. Min Range: -4.4339

Max Act: 4.4339. Min Act: -0.1700

Data Index: 5652234 (Open Web Text)

Max Activating Token Index: 597

Text #1

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.3383. Min Act: -0.1700

Data Index: 52518 (Open Web Text)

Max Activating Token Index: 970

Text #2

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.2823. Min Act: -0.1700

Data Index: 3498444 (Open Web Text)

Max Activating Token Index: 679

Text #3

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.2680. Min Act: -0.1700

Data Index: 5378854 (Open Web Text)

Max Activating Token Index: 842

Text #4

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.2114. Min Act: -0.1700

Data Index: 5975795 (Open Web Text)

Max Activating Token Index: 682

Text #5

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.1890. Min Act: -0.1700

Data Index: 6967971 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.2177. Min Act: -0.1700

Data Index: 4953530 (Open Web Text)

Max Activating Token Index: 512

Text #7

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.2114. Min Act: -0.1700

Data Index: 1914842 (Open Web Text)

Max Activating Token Index: 938

Text #8

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.1374. Min Act: -0.1700

Data Index: 4276793 (Open Web Text)

Max Activating Token Index: 142

Text #9

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.1636. Min Act: -0.1700

Data Index: 8205161 (Open Web Text)

Max Activating Token Index: 212

Text #10

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.1599. Min Act: -0.1700

Data Index: 8175055 (Open Web Text)

Max Activating Token Index: 801

Text #11

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.1331. Min Act: -0.1700

Data Index: 6384032 (Open Web Text)

Max Activating Token Index: 877

Text #12

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.1142. Min Act: -0.1700

Data Index: 7898482 (Open Web Text)

Max Activating Token Index: 532

Text #13

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.0892. Min Act: -0.1700

Data Index: 4509282 (Open Web Text)

Max Activating Token Index: 868

Text #14

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.1111. Min Act: -0.1700

Data Index: 5067343 (Open Web Text)

Max Activating Token Index: 892

Text #15

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.0718. Min Act: -0.1700

Data Index: 7294958 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.0966. Min Act: -0.1700

Data Index: 4321234 (Open Web Text)

Max Activating Token Index: 632

Text #17

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.0784. Min Act: -0.1700

Data Index: 5520339 (Open Web Text)

Max Activating Token Index: 567

Text #18

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.0331. Min Act: -0.1700

Data Index: 6179898 (Open Web Text)

Max Activating Token Index: 856

Text #19

Max Range: 4.4339. Min Range: -4.4339

Max Act: 4.0856. Min Act: -0.1700

Data Index: 6416460 (Open Web Text)

Max Activating Token Index: 492