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

Dataset: Open Web Text

Neuron 592 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: 4.7644. Min Range: -4.7644

Max Act: 4.7605. Min Act: -0.1700

Data Index: 6659514 (Open Web Text)

Max Activating Token Index: 431

Text #1

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.7644. Min Act: -0.1700

Data Index: 4512590 (Open Web Text)

Max Activating Token Index: 541

Text #2

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.7262. Min Act: -0.1700

Data Index: 209844 (Open Web Text)

Max Activating Token Index: 766

Text #3

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.6298. Min Act: -0.1700

Data Index: 7264612 (Open Web Text)

Max Activating Token Index: 441

Text #4

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.6201. Min Act: -0.1700

Data Index: 3885020 (Open Web Text)

Max Activating Token Index: 661

Text #5

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.6464. Min Act: -0.1700

Data Index: 203244 (Open Web Text)

Max Activating Token Index: 847

Text #6

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.6581. Min Act: -0.1700

Data Index: 8391639 (Open Web Text)

Max Activating Token Index: 701

Text #7

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.6509. Min Act: -0.1700

Data Index: 3053956 (Open Web Text)

Max Activating Token Index: 632

Text #8

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.6308. Min Act: -0.1700

Data Index: 2371863 (Open Web Text)

Max Activating Token Index: 272

Text #9

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.6405. Min Act: -0.1700

Data Index: 1878644 (Open Web Text)

Max Activating Token Index: 754

Text #10

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.6109. Min Act: -0.1700

Data Index: 3525949 (Open Web Text)

Max Activating Token Index: 205

Text #11

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.5919. Min Act: -0.1700

Data Index: 795172 (Open Web Text)

Max Activating Token Index: 772

Text #12

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.6158. Min Act: -0.1700

Data Index: 152324 (Open Web Text)

Max Activating Token Index: 551

Text #13

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.6091. Min Act: -0.1700

Data Index: 3219982 (Open Web Text)

Max Activating Token Index: 446

Text #14

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.6035. Min Act: -0.1700

Data Index: 6277862 (Open Web Text)

Max Activating Token Index: 310

Text #15

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.5938. Min Act: -0.1700

Data Index: 3447286 (Open Web Text)

Max Activating Token Index: 1022

Text #16

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.6188. Min Act: -0.1700

Data Index: 6809408 (Open Web Text)

Max Activating Token Index: 256

Text #17

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.5926. Min Act: -0.1700

Data Index: 912071 (Open Web Text)

Max Activating Token Index: 647

Text #18

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.6674. Min Act: -0.1700

Data Index: 7557881 (Open Web Text)

Max Activating Token Index: 522

Text #19

Max Range: 4.7644. Min Range: -4.7644

Max Act: 4.5953. Min Act: -0.1700

Data Index: 1508186 (Open Web Text)

Max Activating Token Index: 795