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

Dataset: Open Web Text

Neuron 1624 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: 2.9165. Min Range: -2.9165

Max Act: 2.9165. Min Act: -0.1700

Data Index: 2803776 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.8735. Min Act: -0.1700

Data Index: 1275213 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.8757. Min Act: -0.1700

Data Index: 7419328 (Open Web Text)

Max Activating Token Index: 20

Text #3

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.8556. Min Act: -0.1700

Data Index: 5400888 (Open Web Text)

Max Activating Token Index: 75

Text #4

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.8324. Min Act: -0.1700

Data Index: 8640897 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.8090. Min Act: -0.1700

Data Index: 6717509 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.8110. Min Act: -0.1700

Data Index: 5108233 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.8133. Min Act: -0.1700

Data Index: 138196 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.7997. Min Act: -0.1700

Data Index: 5162087 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.7787. Min Act: -0.1700

Data Index: 1186253 (Open Web Text)

Max Activating Token Index: 474

Text #10

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.7859. Min Act: -0.1700

Data Index: 621223 (Open Web Text)

Max Activating Token Index: 175

Text #11

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.7691. Min Act: -0.1700

Data Index: 2162759 (Open Web Text)

Max Activating Token Index: 323

Text #12

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.7640. Min Act: -0.1700

Data Index: 2388724 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.7657. Min Act: -0.1700

Data Index: 1098151 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.7535. Min Act: -0.1700

Data Index: 1061621 (Open Web Text)

Max Activating Token Index: 57

Text #15

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.7683. Min Act: -0.1700

Data Index: 7796679 (Open Web Text)

Max Activating Token Index: 9

Text #16

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.7410. Min Act: -0.1700

Data Index: 3909319 (Open Web Text)

Max Activating Token Index: 34

Text #17

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.7403. Min Act: -0.1700

Data Index: 6808517 (Open Web Text)

Max Activating Token Index: 655

Text #18

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.7456. Min Act: -0.1700

Data Index: 7484539 (Open Web Text)

Max Activating Token Index: 440

Text #19

Max Range: 2.9165. Min Range: -2.9165

Max Act: 2.7472. Min Act: -0.1700

Data Index: 4937979 (Open Web Text)

Max Activating Token Index: 933