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

Dataset: Open Web Text

Neuron 2859 in Layer 2

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: 3.5395. Min Range: -3.5395

Max Act: 3.5395. Min Act: -0.1700

Data Index: 2227306 (Open Web Text)

Max Activating Token Index: 137

Text #1

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.4967. Min Act: -0.1700

Data Index: 4000791 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.4857. Min Act: -0.1700

Data Index: 939584 (Open Web Text)

Max Activating Token Index: 11

Text #3

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.4158. Min Act: -0.1700

Data Index: 7974924 (Open Web Text)

Max Activating Token Index: 231

Text #4

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.3914. Min Act: -0.1700

Data Index: 8108631 (Open Web Text)

Max Activating Token Index: 59

Text #5

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.3801. Min Act: -0.1700

Data Index: 462894 (Open Web Text)

Max Activating Token Index: 23

Text #6

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.3677. Min Act: -0.1700

Data Index: 3711606 (Open Web Text)

Max Activating Token Index: 301

Text #7

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.3462. Min Act: -0.1700

Data Index: 3362577 (Open Web Text)

Max Activating Token Index: 356

Text #8

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.3440. Min Act: -0.1700

Data Index: 7216071 (Open Web Text)

Max Activating Token Index: 713

Text #9

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.3502. Min Act: -0.1700

Data Index: 6073198 (Open Web Text)

Max Activating Token Index: 13

Text #10

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.3231. Min Act: -0.1700

Data Index: 6972079 (Open Web Text)

Max Activating Token Index: 284

Text #11

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.3239. Min Act: -0.1700

Data Index: 6834692 (Open Web Text)

Max Activating Token Index: 668

Text #12

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.3283. Min Act: -0.1700

Data Index: 1327462 (Open Web Text)

Max Activating Token Index: 23

Text #13

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.3303. Min Act: -0.1700

Data Index: 2868245 (Open Web Text)

Max Activating Token Index: 1013

Text #14

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.3080. Min Act: -0.1700

Data Index: 1420868 (Open Web Text)

Max Activating Token Index: 454

Text #15

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.2959. Min Act: -0.1700

Data Index: 1820762 (Open Web Text)

Max Activating Token Index: 16

Text #16

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.3110. Min Act: -0.1700

Data Index: 7799226 (Open Web Text)

Max Activating Token Index: 600

Text #17

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.2969. Min Act: -0.1700

Data Index: 2165349 (Open Web Text)

Max Activating Token Index: 569

Text #18

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.3018. Min Act: -0.1700

Data Index: 2420249 (Open Web Text)

Max Activating Token Index: 10

Text #19

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.3034. Min Act: -0.1700

Data Index: 3196458 (Open Web Text)

Max Activating Token Index: 12