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

Dataset: Open Web Text

Neuron 1611 in Layer 0

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: 2.5343. Min Range: -2.5343

Max Act: 2.5343. Min Act: -0.1700

Data Index: 5184684 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.5238. Min Act: -0.1700

Data Index: 6012351 (Open Web Text)

Max Activating Token Index: 764

Text #2

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4929. Min Act: -0.1700

Data Index: 962221 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4866. Min Act: -0.1700

Data Index: 4191491 (Open Web Text)

Max Activating Token Index: 258

Text #4

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4987. Min Act: -0.1700

Data Index: 7746517 (Open Web Text)

Max Activating Token Index: 193

Text #5

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4860. Min Act: -0.1700

Data Index: 7698512 (Open Web Text)

Max Activating Token Index: 1022

Text #6

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4992. Min Act: -0.1700

Data Index: 665136 (Open Web Text)

Max Activating Token Index: 697

Text #7

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.5059. Min Act: -0.1700

Data Index: 505416 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4735. Min Act: -0.1700

Data Index: 4155692 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4786. Min Act: -0.1700

Data Index: 3554599 (Open Web Text)

Max Activating Token Index: 728

Text #10

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4758. Min Act: -0.1700

Data Index: 688577 (Open Web Text)

Max Activating Token Index: 7

Text #11

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4785. Min Act: -0.1700

Data Index: 7496036 (Open Web Text)

Max Activating Token Index: 1005

Text #12

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4762. Min Act: -0.1700

Data Index: 5332591 (Open Web Text)

Max Activating Token Index: 128

Text #13

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4681. Min Act: -0.1700

Data Index: 8621432 (Open Web Text)

Max Activating Token Index: 360

Text #14

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4717. Min Act: -0.1700

Data Index: 85468 (Open Web Text)

Max Activating Token Index: 257

Text #15

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4711. Min Act: -0.1700

Data Index: 2467720 (Open Web Text)

Max Activating Token Index: 914

Text #16

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4704. Min Act: -0.1700

Data Index: 2650781 (Open Web Text)

Max Activating Token Index: 123

Text #17

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4620. Min Act: -0.1700

Data Index: 760357 (Open Web Text)

Max Activating Token Index: 905

Text #18

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4550. Min Act: -0.1700

Data Index: 2522706 (Open Web Text)

Max Activating Token Index: 278

Text #19

Max Range: 2.5343. Min Range: -2.5343

Max Act: 2.4577. Min Act: -0.1700

Data Index: 4934416 (Open Web Text)

Max Activating Token Index: 843