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

Dataset: Open Web Text

Neuron 66 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: 3.0529. Min Range: -3.0529

Max Act: 3.0529. Min Act: -0.1700

Data Index: 8569785 (Open Web Text)

Max Activating Token Index: 197

Text #1

Max Range: 3.0529. Min Range: -3.0529

Max Act: 3.0144. Min Act: -0.1700

Data Index: 2156895 (Open Web Text)

Max Activating Token Index: 592

Text #2

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9551. Min Act: -0.1700

Data Index: 6556600 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9391. Min Act: -0.1700

Data Index: 1761397 (Open Web Text)

Max Activating Token Index: 425

Text #4

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9537. Min Act: -0.1700

Data Index: 2897046 (Open Web Text)

Max Activating Token Index: 764

Text #5

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9347. Min Act: -0.1700

Data Index: 5801249 (Open Web Text)

Max Activating Token Index: 917

Text #6

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.9063. Min Act: -0.1700

Data Index: 3972647 (Open Web Text)

Max Activating Token Index: 160

Text #7

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8743. Min Act: -0.1700

Data Index: 3779907 (Open Web Text)

Max Activating Token Index: 657

Text #8

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8771. Min Act: -0.1700

Data Index: 8480924 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8694. Min Act: -0.1700

Data Index: 3371472 (Open Web Text)

Max Activating Token Index: 1016

Text #10

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8671. Min Act: -0.1700

Data Index: 3371995 (Open Web Text)

Max Activating Token Index: 668

Text #11

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8659. Min Act: -0.1700

Data Index: 8606296 (Open Web Text)

Max Activating Token Index: 651

Text #12

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8500. Min Act: -0.1700

Data Index: 503596 (Open Web Text)

Max Activating Token Index: 631

Text #13

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8550. Min Act: -0.1700

Data Index: 5600899 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8767. Min Act: -0.1700

Data Index: 8276693 (Open Web Text)

Max Activating Token Index: 90

Text #15

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8352. Min Act: -0.1700

Data Index: 6373445 (Open Web Text)

Max Activating Token Index: 606

Text #16

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8387. Min Act: -0.1700

Data Index: 68249 (Open Web Text)

Max Activating Token Index: 756

Text #17

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.8157. Min Act: -0.1700

Data Index: 7094950 (Open Web Text)

Max Activating Token Index: 853

Text #18

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.7838. Min Act: -0.1700

Data Index: 785177 (Open Web Text)

Max Activating Token Index: 325

Text #19

Max Range: 3.0529. Min Range: -3.0529

Max Act: 2.7834. Min Act: -0.1700

Data Index: 3818293 (Open Web Text)

Max Activating Token Index: 734