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

Dataset: Open Web Text

Neuron 2116 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: 3.5677. Min Range: -3.5677

Max Act: 3.5677. Min Act: -0.1700

Data Index: 2388607 (Open Web Text)

Max Activating Token Index: 105

Text #1

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.4294. Min Act: -0.1700

Data Index: 1312568 (Open Web Text)

Max Activating Token Index: 890

Text #2

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.4056. Min Act: -0.1700

Data Index: 3264384 (Open Web Text)

Max Activating Token Index: 409

Text #3

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3991. Min Act: -0.1700

Data Index: 5327544 (Open Web Text)

Max Activating Token Index: 112

Text #4

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3564. Min Act: -0.1700

Data Index: 8408946 (Open Web Text)

Max Activating Token Index: 754

Text #5

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3772. Min Act: -0.1700

Data Index: 6007743 (Open Web Text)

Max Activating Token Index: 700

Text #6

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.4040. Min Act: -0.1700

Data Index: 7551071 (Open Web Text)

Max Activating Token Index: 1002

Text #7

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3903. Min Act: -0.1700

Data Index: 4125922 (Open Web Text)

Max Activating Token Index: 918

Text #8

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3653. Min Act: -0.1700

Data Index: 6558068 (Open Web Text)

Max Activating Token Index: 430

Text #9

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3688. Min Act: -0.1700

Data Index: 3429740 (Open Web Text)

Max Activating Token Index: 529

Text #10

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3564. Min Act: -0.1700

Data Index: 4370940 (Open Web Text)

Max Activating Token Index: 271

Text #11

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3269. Min Act: -0.1700

Data Index: 570699 (Open Web Text)

Max Activating Token Index: 898

Text #12

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3292. Min Act: -0.1700

Data Index: 7371368 (Open Web Text)

Max Activating Token Index: 963

Text #13

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3311. Min Act: -0.1700

Data Index: 1783230 (Open Web Text)

Max Activating Token Index: 831

Text #14

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3175. Min Act: -0.1700

Data Index: 1886159 (Open Web Text)

Max Activating Token Index: 363

Text #15

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3312. Min Act: -0.1700

Data Index: 3429742 (Open Web Text)

Max Activating Token Index: 322

Text #16

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3264. Min Act: -0.1700

Data Index: 7944045 (Open Web Text)

Max Activating Token Index: 606

Text #17

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3104. Min Act: -0.1700

Data Index: 4573149 (Open Web Text)

Max Activating Token Index: 318

Text #18

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3071. Min Act: -0.1700

Data Index: 242004 (Open Web Text)

Max Activating Token Index: 283

Text #19

Max Range: 3.5677. Min Range: -3.5677

Max Act: 3.3134. Min Act: -0.1700

Data Index: 7690397 (Open Web Text)

Max Activating Token Index: 33