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

Dataset: Open Web Text

Neuron 428 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: 3.6724. Min Range: -3.6724

Max Act: 3.6724. Min Act: -0.1700

Data Index: 4188623 (Open Web Text)

Max Activating Token Index: 344

Text #1

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.6521. Min Act: -0.1700

Data Index: 7388996 (Open Web Text)

Max Activating Token Index: 377

Text #2

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.5822. Min Act: -0.1700

Data Index: 2876117 (Open Web Text)

Max Activating Token Index: 816

Text #3

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.5163. Min Act: -0.1700

Data Index: 3539312 (Open Web Text)

Max Activating Token Index: 641

Text #4

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.5244. Min Act: -0.1700

Data Index: 6007042 (Open Web Text)

Max Activating Token Index: 978

Text #5

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.5184. Min Act: -0.1700

Data Index: 5074582 (Open Web Text)

Max Activating Token Index: 262

Text #6

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.5188. Min Act: -0.1700

Data Index: 8338188 (Open Web Text)

Max Activating Token Index: 414

Text #7

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.5030. Min Act: -0.1700

Data Index: 5573054 (Open Web Text)

Max Activating Token Index: 432

Text #8

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.5058. Min Act: -0.1700

Data Index: 7069245 (Open Web Text)

Max Activating Token Index: 897

Text #9

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.4968. Min Act: -0.1700

Data Index: 7578491 (Open Web Text)

Max Activating Token Index: 888

Text #10

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.5230. Min Act: -0.1700

Data Index: 4043507 (Open Web Text)

Max Activating Token Index: 535

Text #11

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.5319. Min Act: -0.1700

Data Index: 5144534 (Open Web Text)

Max Activating Token Index: 939

Text #12

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.4849. Min Act: -0.1700

Data Index: 8267879 (Open Web Text)

Max Activating Token Index: 340

Text #13

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.5247. Min Act: -0.1700

Data Index: 6349907 (Open Web Text)

Max Activating Token Index: 847

Text #14

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.4764. Min Act: -0.1700

Data Index: 8793412 (Open Web Text)

Max Activating Token Index: 562

Text #15

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.4882. Min Act: -0.1700

Data Index: 8340573 (Open Web Text)

Max Activating Token Index: 454

Text #16

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.5003. Min Act: -0.1700

Data Index: 7604764 (Open Web Text)

Max Activating Token Index: 470

Text #17

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.4645. Min Act: -0.1700

Data Index: 2586795 (Open Web Text)

Max Activating Token Index: 969

Text #18

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.4522. Min Act: -0.1700

Data Index: 1088574 (Open Web Text)

Max Activating Token Index: 570

Text #19

Max Range: 3.6724. Min Range: -3.6724

Max Act: 3.4523. Min Act: -0.1700

Data Index: 5919943 (Open Web Text)

Max Activating Token Index: 471