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

Dataset: Open Web Text

Neuron 740 in Layer 6

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: 5.6325. Min Range: -5.6325

Max Act: 5.6325. Min Act: -0.1700

Data Index: 370712 (Open Web Text)

Max Activating Token Index: 846

Text #1

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.6066. Min Act: -0.1700

Data Index: 6314478 (Open Web Text)

Max Activating Token Index: 230

Text #2

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.5471. Min Act: -0.1700

Data Index: 7601296 (Open Web Text)

Max Activating Token Index: 752

Text #3

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.5782. Min Act: -0.1700

Data Index: 6802585 (Open Web Text)

Max Activating Token Index: 750

Text #4

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.4998. Min Act: -0.1700

Data Index: 3366475 (Open Web Text)

Max Activating Token Index: 675

Text #5

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.5599. Min Act: -0.1700

Data Index: 1702308 (Open Web Text)

Max Activating Token Index: 458

Text #6

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.5021. Min Act: -0.1700

Data Index: 8782568 (Open Web Text)

Max Activating Token Index: 712

Text #7

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.5391. Min Act: -0.1700

Data Index: 2337102 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.4784. Min Act: -0.1700

Data Index: 7206182 (Open Web Text)

Max Activating Token Index: 994

Text #9

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.4824. Min Act: -0.1700

Data Index: 2017984 (Open Web Text)

Max Activating Token Index: 444

Text #10

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.4334. Min Act: -0.1700

Data Index: 6055920 (Open Web Text)

Max Activating Token Index: 866

Text #11

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.4823. Min Act: -0.1700

Data Index: 1216557 (Open Web Text)

Max Activating Token Index: 318

Text #12

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.4885. Min Act: -0.1700

Data Index: 8658205 (Open Web Text)

Max Activating Token Index: 426

Text #13

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.4914. Min Act: -0.1700

Data Index: 6249064 (Open Web Text)

Max Activating Token Index: 638

Text #14

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.4150. Min Act: -0.1700

Data Index: 4220418 (Open Web Text)

Max Activating Token Index: 227

Text #15

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.4473. Min Act: -0.1699

Data Index: 3542408 (Open Web Text)

Max Activating Token Index: 380

Text #16

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.4141. Min Act: -0.1698

Data Index: 7289169 (Open Web Text)

Max Activating Token Index: 949

Text #17

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.4556. Min Act: -0.1700

Data Index: 8506459 (Open Web Text)

Max Activating Token Index: 354

Text #18

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.4102. Min Act: -0.1700

Data Index: 7916711 (Open Web Text)

Max Activating Token Index: 813

Text #19

Max Range: 5.6325. Min Range: -5.6325

Max Act: 5.4215. Min Act: -0.1700

Data Index: 1019113 (Open Web Text)

Max Activating Token Index: 944