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

Dataset: Open Web Text

Neuron 2075 in Layer 3

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: 4.1947. Min Range: -4.1947

Max Act: 4.1947. Min Act: -0.1700

Data Index: 4634620 (Open Web Text)

Max Activating Token Index: 944

Text #1

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.9501. Min Act: -0.1700

Data Index: 1408550 (Open Web Text)

Max Activating Token Index: 1012

Text #2

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.9794. Min Act: -0.1700

Data Index: 4041699 (Open Web Text)

Max Activating Token Index: 823

Text #3

Max Range: 4.1947. Min Range: -4.1947

Max Act: 4.0075. Min Act: -0.1700

Data Index: 7197005 (Open Web Text)

Max Activating Token Index: 889

Text #4

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.9928. Min Act: -0.1700

Data Index: 2881164 (Open Web Text)

Max Activating Token Index: 570

Text #5

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.9559. Min Act: -0.1700

Data Index: 3539893 (Open Web Text)

Max Activating Token Index: 799

Text #6

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.9143. Min Act: -0.1700

Data Index: 6255159 (Open Web Text)

Max Activating Token Index: 677

Text #7

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.8654. Min Act: -0.1700

Data Index: 1017952 (Open Web Text)

Max Activating Token Index: 424

Text #8

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.8847. Min Act: -0.1700

Data Index: 4963484 (Open Web Text)

Max Activating Token Index: 889

Text #9

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.8880. Min Act: -0.1700

Data Index: 5396476 (Open Web Text)

Max Activating Token Index: 713

Text #10

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.8841. Min Act: -0.1700

Data Index: 8209732 (Open Web Text)

Max Activating Token Index: 504

Text #11

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.8485. Min Act: -0.1700

Data Index: 8587528 (Open Web Text)

Max Activating Token Index: 442

Text #12

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.8673. Min Act: -0.1700

Data Index: 8623620 (Open Web Text)

Max Activating Token Index: 830

Text #13

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.8077. Min Act: -0.1700

Data Index: 5028697 (Open Web Text)

Max Activating Token Index: 642

Text #14

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.8473. Min Act: -0.1700

Data Index: 3720212 (Open Web Text)

Max Activating Token Index: 754

Text #15

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.8106. Min Act: -0.1700

Data Index: 4112158 (Open Web Text)

Max Activating Token Index: 852

Text #16

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.8150. Min Act: -0.1700

Data Index: 159926 (Open Web Text)

Max Activating Token Index: 981

Text #17

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.8140. Min Act: -0.1700

Data Index: 5971560 (Open Web Text)

Max Activating Token Index: 859

Text #18

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.8184. Min Act: -0.1700

Data Index: 6206824 (Open Web Text)

Max Activating Token Index: 822

Text #19

Max Range: 4.1947. Min Range: -4.1947

Max Act: 3.8238. Min Act: -0.1700

Data Index: 6680434 (Open Web Text)

Max Activating Token Index: 541