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

Dataset: Open Web Text

Neuron 1839 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: 2.6401. Min Range: -2.6401

Max Act: 2.5985. Min Act: -0.1700

Data Index: 3272668 (Open Web Text)

Max Activating Token Index: 847

Text #1

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.6401. Min Act: -0.1700

Data Index: 1508602 (Open Web Text)

Max Activating Token Index: 989

Text #2

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.5901. Min Act: -0.1700

Data Index: 1825721 (Open Web Text)

Max Activating Token Index: 874

Text #3

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.5780. Min Act: -0.1700

Data Index: 8730539 (Open Web Text)

Max Activating Token Index: 312

Text #4

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.6083. Min Act: -0.1700

Data Index: 7306796 (Open Web Text)

Max Activating Token Index: 382

Text #5

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.5946. Min Act: -0.1700

Data Index: 2379261 (Open Web Text)

Max Activating Token Index: 315

Text #6

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.5795. Min Act: -0.1700

Data Index: 4382095 (Open Web Text)

Max Activating Token Index: 765

Text #7

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.5524. Min Act: -0.1700

Data Index: 7188279 (Open Web Text)

Max Activating Token Index: 973

Text #8

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.5528. Min Act: -0.1700

Data Index: 7169009 (Open Web Text)

Max Activating Token Index: 1002

Text #9

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.5391. Min Act: -0.1700

Data Index: 2009391 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.5277. Min Act: -0.1700

Data Index: 6505167 (Open Web Text)

Max Activating Token Index: 245

Text #11

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.5293. Min Act: -0.1700

Data Index: 2459548 (Open Web Text)

Max Activating Token Index: 734

Text #12

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.5301. Min Act: -0.1700

Data Index: 1000725 (Open Web Text)

Max Activating Token Index: 973

Text #13

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.5256. Min Act: -0.1700

Data Index: 1587604 (Open Web Text)

Max Activating Token Index: 584

Text #14

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.5110. Min Act: -0.1700

Data Index: 6636593 (Open Web Text)

Max Activating Token Index: 922

Text #15

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.4864. Min Act: -0.1700

Data Index: 6126757 (Open Web Text)

Max Activating Token Index: 347

Text #16

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.4801. Min Act: -0.1700

Data Index: 3654930 (Open Web Text)

Max Activating Token Index: 912

Text #17

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.5089. Min Act: -0.1700

Data Index: 4206408 (Open Web Text)

Max Activating Token Index: 382

Text #18

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.5337. Min Act: -0.1700

Data Index: 7308953 (Open Web Text)

Max Activating Token Index: 285

Text #19

Max Range: 2.6401. Min Range: -2.6401

Max Act: 2.4985. Min Act: -0.1700

Data Index: 8470205 (Open Web Text)

Max Activating Token Index: 203