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

Dataset: Open Web Text

Neuron 252 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: 3.6378. Min Range: -3.6378

Max Act: 3.6013. Min Act: -0.1700

Data Index: 5034306 (Open Web Text)

Max Activating Token Index: 768

Text #1

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.6258. Min Act: -0.1700

Data Index: 35437 (Open Web Text)

Max Activating Token Index: 972

Text #2

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.6378. Min Act: -0.1700

Data Index: 6759519 (Open Web Text)

Max Activating Token Index: 522

Text #3

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.5649. Min Act: -0.1700

Data Index: 4580735 (Open Web Text)

Max Activating Token Index: 272

Text #4

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.5245. Min Act: -0.1700

Data Index: 3061286 (Open Web Text)

Max Activating Token Index: 90

Text #5

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.4875. Min Act: -0.1700

Data Index: 4968082 (Open Web Text)

Max Activating Token Index: 998

Text #6

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.5136. Min Act: -0.1700

Data Index: 6868161 (Open Web Text)

Max Activating Token Index: 347

Text #7

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.4533. Min Act: -0.1700

Data Index: 967031 (Open Web Text)

Max Activating Token Index: 146

Text #8

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.4220. Min Act: -0.1700

Data Index: 5627883 (Open Web Text)

Max Activating Token Index: 386

Text #9

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.3890. Min Act: -0.1700

Data Index: 6079025 (Open Web Text)

Max Activating Token Index: 394

Text #10

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.4237. Min Act: -0.1700

Data Index: 6347792 (Open Web Text)

Max Activating Token Index: 576

Text #11

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.4051. Min Act: -0.1700

Data Index: 8289133 (Open Web Text)

Max Activating Token Index: 825

Text #12

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.4773. Min Act: -0.1700

Data Index: 1567926 (Open Web Text)

Max Activating Token Index: 464

Text #13

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.3718. Min Act: -0.1700

Data Index: 967030 (Open Web Text)

Max Activating Token Index: 830

Text #14

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.4122. Min Act: -0.1700

Data Index: 3504318 (Open Web Text)

Max Activating Token Index: 381

Text #15

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.3848. Min Act: -0.1700

Data Index: 3126966 (Open Web Text)

Max Activating Token Index: 468

Text #16

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.3062. Min Act: -0.1700

Data Index: 4665302 (Open Web Text)

Max Activating Token Index: 779

Text #17

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.3775. Min Act: -0.1700

Data Index: 3353697 (Open Web Text)

Max Activating Token Index: 587

Text #18

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.4184. Min Act: -0.1700

Data Index: 597883 (Open Web Text)

Max Activating Token Index: 144

Text #19

Max Range: 3.6378. Min Range: -3.6378

Max Act: 3.3450. Min Act: -0.1700

Data Index: 2227408 (Open Web Text)

Max Activating Token Index: 946