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

Dataset: Open Web Text

Neuron 2467 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: 3.1716. Min Range: -3.1716

Max Act: 3.1716. Min Act: -0.1700

Data Index: 3083123 (Open Web Text)

Max Activating Token Index: 638

Text #1

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.1188. Min Act: -0.1700

Data Index: 2237044 (Open Web Text)

Max Activating Token Index: 1011

Text #2

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.1041. Min Act: -0.1700

Data Index: 3367640 (Open Web Text)

Max Activating Token Index: 904

Text #3

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.1090. Min Act: -0.1700

Data Index: 1585582 (Open Web Text)

Max Activating Token Index: 536

Text #4

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.0988. Min Act: -0.1700

Data Index: 2268292 (Open Web Text)

Max Activating Token Index: 694

Text #5

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.1228. Min Act: -0.1700

Data Index: 8284466 (Open Web Text)

Max Activating Token Index: 939

Text #6

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.0947. Min Act: -0.1700

Data Index: 3037229 (Open Web Text)

Max Activating Token Index: 613

Text #7

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.0862. Min Act: -0.1700

Data Index: 5630344 (Open Web Text)

Max Activating Token Index: 163

Text #8

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.0741. Min Act: -0.1700

Data Index: 8492880 (Open Web Text)

Max Activating Token Index: 248

Text #9

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.0651. Min Act: -0.1700

Data Index: 6880833 (Open Web Text)

Max Activating Token Index: 902

Text #10

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.0564. Min Act: -0.1700

Data Index: 6580518 (Open Web Text)

Max Activating Token Index: 680

Text #11

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.0633. Min Act: -0.1700

Data Index: 336852 (Open Web Text)

Max Activating Token Index: 116

Text #12

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.0732. Min Act: -0.1700

Data Index: 5012876 (Open Web Text)

Max Activating Token Index: 468

Text #13

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.0156. Min Act: -0.1700

Data Index: 6373601 (Open Web Text)

Max Activating Token Index: 972

Text #14

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.0277. Min Act: -0.1700

Data Index: 5089143 (Open Web Text)

Max Activating Token Index: 444

Text #15

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.0310. Min Act: -0.1700

Data Index: 4254168 (Open Web Text)

Max Activating Token Index: 21

Text #16

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.0193. Min Act: -0.1700

Data Index: 1088199 (Open Web Text)

Max Activating Token Index: 416

Text #17

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.0180. Min Act: -0.1700

Data Index: 2912851 (Open Web Text)

Max Activating Token Index: 21

Text #18

Max Range: 3.1716. Min Range: -3.1716

Max Act: 3.0103. Min Act: -0.1700

Data Index: 2082075 (Open Web Text)

Max Activating Token Index: 967

Text #19

Max Range: 3.1716. Min Range: -3.1716

Max Act: 2.9975. Min Act: -0.1700

Data Index: 1088186 (Open Web Text)

Max Activating Token Index: 33