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

Dataset: Open Web Text

Neuron 519 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: 3.6870. Min Range: -3.6870

Max Act: 3.6870. Min Act: -0.1700

Data Index: 6591133 (Open Web Text)

Max Activating Token Index: 74

Text #1

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.6636. Min Act: -0.1700

Data Index: 4093961 (Open Web Text)

Max Activating Token Index: 1009

Text #2

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.6161. Min Act: -0.1700

Data Index: 7899176 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.5452. Min Act: -0.1700

Data Index: 848048 (Open Web Text)

Max Activating Token Index: 689

Text #4

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.5167. Min Act: -0.1700

Data Index: 3024285 (Open Web Text)

Max Activating Token Index: 348

Text #5

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.5972. Min Act: -0.1700

Data Index: 989061 (Open Web Text)

Max Activating Token Index: 505

Text #6

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.5637. Min Act: -0.1700

Data Index: 5441708 (Open Web Text)

Max Activating Token Index: 666

Text #7

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.5397. Min Act: -0.1700

Data Index: 66607 (Open Web Text)

Max Activating Token Index: 488

Text #8

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.5288. Min Act: -0.1700

Data Index: 6677876 (Open Web Text)

Max Activating Token Index: 760

Text #9

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.5078. Min Act: -0.1700

Data Index: 5441707 (Open Web Text)

Max Activating Token Index: 993

Text #10

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.5082. Min Act: -0.1700

Data Index: 4125680 (Open Web Text)

Max Activating Token Index: 486

Text #11

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4627. Min Act: -0.1700

Data Index: 2825314 (Open Web Text)

Max Activating Token Index: 470

Text #12

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4746. Min Act: -0.1700

Data Index: 1910673 (Open Web Text)

Max Activating Token Index: 124

Text #13

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4863. Min Act: -0.1700

Data Index: 4954222 (Open Web Text)

Max Activating Token Index: 12

Text #14

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4666. Min Act: -0.1700

Data Index: 6341236 (Open Web Text)

Max Activating Token Index: 220

Text #15

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4924. Min Act: -0.1700

Data Index: 4929838 (Open Web Text)

Max Activating Token Index: 654

Text #16

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4897. Min Act: -0.1700

Data Index: 2661611 (Open Web Text)

Max Activating Token Index: 169

Text #17

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4236. Min Act: -0.1700

Data Index: 7643293 (Open Web Text)

Max Activating Token Index: 227

Text #18

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4596. Min Act: -0.1700

Data Index: 2388996 (Open Web Text)

Max Activating Token Index: 48

Text #19

Max Range: 3.6870. Min Range: -3.6870

Max Act: 3.4878. Min Act: -0.1700

Data Index: 5256324 (Open Web Text)

Max Activating Token Index: 383