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

Dataset: Open Web Text

Neuron 2971 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: 3.9934. Min Range: -3.9934

Max Act: 3.9934. Min Act: -0.1700

Data Index: 3539630 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.9805. Min Act: -0.1700

Data Index: 1345149 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.9524. Min Act: -0.1700

Data Index: 4548486 (Open Web Text)

Max Activating Token Index: 3

Text #3

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.9712. Min Act: -0.1700

Data Index: 7469128 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.9265. Min Act: -0.1700

Data Index: 8362078 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.9209. Min Act: -0.1700

Data Index: 2490926 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.9205. Min Act: -0.1700

Data Index: 1707431 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.9300. Min Act: -0.1700

Data Index: 2711703 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.8967. Min Act: -0.1700

Data Index: 6365919 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.9107. Min Act: -0.1700

Data Index: 23754 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.8634. Min Act: -0.1700

Data Index: 321025 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.8791. Min Act: -0.1700

Data Index: 8289412 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.8699. Min Act: -0.1700

Data Index: 2989905 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.8645. Min Act: -0.1700

Data Index: 4407163 (Open Web Text)

Max Activating Token Index: 7

Text #14

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.8652. Min Act: -0.1700

Data Index: 95434 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.8677. Min Act: -0.1700

Data Index: 2309965 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.8413. Min Act: -0.1700

Data Index: 4151407 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.8526. Min Act: -0.1700

Data Index: 1791331 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.8258. Min Act: -0.1700

Data Index: 629488 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 3.9934. Min Range: -3.9934

Max Act: 3.8300. Min Act: -0.1700

Data Index: 658476 (Open Web Text)

Max Activating Token Index: 4