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

Dataset: Open Web Text

Neuron 69 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: 5.8472. Min Range: -5.8472

Max Act: 5.8472. Min Act: -0.1700

Data Index: 7920056 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.8141. Min Act: -0.1700

Data Index: 5956347 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.8126. Min Act: -0.1700

Data Index: 6481219 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.8234. Min Act: -0.1700

Data Index: 6552536 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.8102. Min Act: -0.1700

Data Index: 7020355 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.7937. Min Act: -0.1700

Data Index: 5918918 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.7805. Min Act: -0.1700

Data Index: 2707598 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.7654. Min Act: -0.1700

Data Index: 1072883 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.7680. Min Act: -0.1700

Data Index: 4275013 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.7651. Min Act: -0.1700

Data Index: 1828670 (Open Web Text)

Max Activating Token Index: 6

Text #10

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.7388. Min Act: -0.1700

Data Index: 1899724 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.7616. Min Act: -0.1700

Data Index: 4597924 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.7676. Min Act: -0.1700

Data Index: 4182593 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.7551. Min Act: -0.1700

Data Index: 7465580 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.7432. Min Act: -0.1700

Data Index: 3878584 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.7468. Min Act: -0.1700

Data Index: 2067654 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.7584. Min Act: -0.1700

Data Index: 2037665 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.7064. Min Act: -0.1700

Data Index: 4257496 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.7170. Min Act: -0.1700

Data Index: 2535001 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 5.8472. Min Range: -5.8472

Max Act: 5.7058. Min Act: -0.1700

Data Index: 5088581 (Open Web Text)

Max Activating Token Index: 4