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

Dataset: Open Web Text

Neuron 190 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: 4.0348. Min Range: -4.0348

Max Act: 4.0348. Min Act: -0.1700

Data Index: 6790294 (Open Web Text)

Max Activating Token Index: 943

Text #1

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.9732. Min Act: -0.1700

Data Index: 1598298 (Open Web Text)

Max Activating Token Index: 205

Text #2

Max Range: 4.0348. Min Range: -4.0348

Max Act: 4.0012. Min Act: -0.1700

Data Index: 4180000 (Open Web Text)

Max Activating Token Index: 137

Text #3

Max Range: 4.0348. Min Range: -4.0348

Max Act: 4.0157. Min Act: -0.1700

Data Index: 5043839 (Open Web Text)

Max Activating Token Index: 644

Text #4

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.9307. Min Act: -0.1700

Data Index: 4421361 (Open Web Text)

Max Activating Token Index: 109

Text #5

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.9719. Min Act: -0.1700

Data Index: 4719017 (Open Web Text)

Max Activating Token Index: 932

Text #6

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.9225. Min Act: -0.1700

Data Index: 8428780 (Open Web Text)

Max Activating Token Index: 801

Text #7

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.9355. Min Act: -0.1700

Data Index: 473097 (Open Web Text)

Max Activating Token Index: 465

Text #8

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.8921. Min Act: -0.1700

Data Index: 3810008 (Open Web Text)

Max Activating Token Index: 268

Text #9

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.9164. Min Act: -0.1700

Data Index: 7754075 (Open Web Text)

Max Activating Token Index: 258

Text #10

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.9066. Min Act: -0.1700

Data Index: 4579458 (Open Web Text)

Max Activating Token Index: 73

Text #11

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.9146. Min Act: -0.1700

Data Index: 7839144 (Open Web Text)

Max Activating Token Index: 990

Text #12

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.8694. Min Act: -0.1700

Data Index: 1307009 (Open Web Text)

Max Activating Token Index: 762

Text #13

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.8592. Min Act: -0.1700

Data Index: 1865917 (Open Web Text)

Max Activating Token Index: 893

Text #14

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.8669. Min Act: -0.1700

Data Index: 4698261 (Open Web Text)

Max Activating Token Index: 855

Text #15

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.8951. Min Act: -0.1700

Data Index: 1071197 (Open Web Text)

Max Activating Token Index: 810

Text #16

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.8556. Min Act: -0.1700

Data Index: 2594759 (Open Web Text)

Max Activating Token Index: 904

Text #17

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.8463. Min Act: -0.1700

Data Index: 1420711 (Open Web Text)

Max Activating Token Index: 739

Text #18

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.8718. Min Act: -0.1700

Data Index: 2233594 (Open Web Text)

Max Activating Token Index: 669

Text #19

Max Range: 4.0348. Min Range: -4.0348

Max Act: 3.8662. Min Act: -0.1700

Data Index: 2482647 (Open Web Text)

Max Activating Token Index: 214