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

Dataset: Open Web Text

Neuron 2809 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: 5.4243. Min Range: -5.4243

Max Act: 5.4243. Min Act: -0.1700

Data Index: 3068547 (Open Web Text)

Max Activating Token Index: 38

Text #1

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.3827. Min Act: -0.1700

Data Index: 1726114 (Open Web Text)

Max Activating Token Index: 591

Text #2

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.2557. Min Act: -0.1700

Data Index: 3818686 (Open Web Text)

Max Activating Token Index: 330

Text #3

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.2564. Min Act: -0.1700

Data Index: 6160814 (Open Web Text)

Max Activating Token Index: 519

Text #4

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.2407. Min Act: -0.1700

Data Index: 5904501 (Open Web Text)

Max Activating Token Index: 965

Text #5

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.1930. Min Act: -0.1700

Data Index: 627699 (Open Web Text)

Max Activating Token Index: 870

Text #6

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.2205. Min Act: -0.1700

Data Index: 6084255 (Open Web Text)

Max Activating Token Index: 872

Text #7

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.1986. Min Act: -0.1700

Data Index: 3831910 (Open Web Text)

Max Activating Token Index: 513

Text #8

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.2146. Min Act: -0.1700

Data Index: 6253901 (Open Web Text)

Max Activating Token Index: 272

Text #9

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.1069. Min Act: -0.1700

Data Index: 1518572 (Open Web Text)

Max Activating Token Index: 703

Text #10

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.1220. Min Act: -0.1700

Data Index: 4338414 (Open Web Text)

Max Activating Token Index: 888

Text #11

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.1337. Min Act: -0.1700

Data Index: 1855691 (Open Web Text)

Max Activating Token Index: 942

Text #12

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.0827. Min Act: -0.1700

Data Index: 5062299 (Open Web Text)

Max Activating Token Index: 231

Text #13

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.0807. Min Act: -0.1700

Data Index: 2754731 (Open Web Text)

Max Activating Token Index: 323

Text #14

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.1008. Min Act: -0.1700

Data Index: 1400059 (Open Web Text)

Max Activating Token Index: 831

Text #15

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.0687. Min Act: -0.1700

Data Index: 3949881 (Open Web Text)

Max Activating Token Index: 283

Text #16

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.1172. Min Act: -0.1700

Data Index: 4796904 (Open Web Text)

Max Activating Token Index: 888

Text #17

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.0605. Min Act: -0.1700

Data Index: 5452691 (Open Web Text)

Max Activating Token Index: 922

Text #18

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.0693. Min Act: -0.1700

Data Index: 5144344 (Open Web Text)

Max Activating Token Index: 291

Text #19

Max Range: 5.4243. Min Range: -5.4243

Max Act: 5.0735. Min Act: -0.1700

Data Index: 356858 (Open Web Text)

Max Activating Token Index: 442