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

Dataset: Open Web Text

Neuron 1713 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: 4.3226. Min Range: -4.3226

Max Act: 4.3226. Min Act: -0.1700

Data Index: 4869143 (Open Web Text)

Max Activating Token Index: 401

Text #1

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.2868. Min Act: -0.1700

Data Index: 3121751 (Open Web Text)

Max Activating Token Index: 468

Text #2

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.2586. Min Act: -0.1700

Data Index: 5182675 (Open Web Text)

Max Activating Token Index: 237

Text #3

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.2872. Min Act: -0.1700

Data Index: 6863810 (Open Web Text)

Max Activating Token Index: 347

Text #4

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.2429. Min Act: -0.1700

Data Index: 8209587 (Open Web Text)

Max Activating Token Index: 1013

Text #5

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.2650. Min Act: -0.1700

Data Index: 3667644 (Open Web Text)

Max Activating Token Index: 391

Text #6

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.2219. Min Act: -0.1700

Data Index: 6396647 (Open Web Text)

Max Activating Token Index: 886

Text #7

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.2014. Min Act: -0.1700

Data Index: 986264 (Open Web Text)

Max Activating Token Index: 448

Text #8

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.2241. Min Act: -0.1700

Data Index: 5851787 (Open Web Text)

Max Activating Token Index: 677

Text #9

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.2138. Min Act: -0.1700

Data Index: 502904 (Open Web Text)

Max Activating Token Index: 175

Text #10

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.2101. Min Act: -0.1700

Data Index: 3732721 (Open Web Text)

Max Activating Token Index: 492

Text #11

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.2016. Min Act: -0.1700

Data Index: 3732720 (Open Web Text)

Max Activating Token Index: 970

Text #12

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.1898. Min Act: -0.1700

Data Index: 391855 (Open Web Text)

Max Activating Token Index: 521

Text #13

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.1673. Min Act: -0.1700

Data Index: 8085820 (Open Web Text)

Max Activating Token Index: 347

Text #14

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.1874. Min Act: -0.1700

Data Index: 4404308 (Open Web Text)

Max Activating Token Index: 230

Text #15

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.1995. Min Act: -0.1700

Data Index: 266949 (Open Web Text)

Max Activating Token Index: 431

Text #16

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.1721. Min Act: -0.1700

Data Index: 6218047 (Open Web Text)

Max Activating Token Index: 862

Text #17

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.1734. Min Act: -0.1700

Data Index: 5465857 (Open Web Text)

Max Activating Token Index: 472

Text #18

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.1875. Min Act: -0.1700

Data Index: 3489114 (Open Web Text)

Max Activating Token Index: 865

Text #19

Max Range: 4.3226. Min Range: -4.3226

Max Act: 4.1732. Min Act: -0.1700

Data Index: 5120254 (Open Web Text)

Max Activating Token Index: 395