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

Dataset: Open Web Text

Neuron 76 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: 3.2631. Min Range: -3.2631

Max Act: 3.2631. Min Act: -0.1700

Data Index: 3712249 (Open Web Text)

Max Activating Token Index: 48

Text #1

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.2510. Min Act: -0.1700

Data Index: 4254085 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.2344. Min Act: -0.1700

Data Index: 3196395 (Open Web Text)

Max Activating Token Index: 7

Text #3

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.2073. Min Act: -0.1700

Data Index: 7951989 (Open Web Text)

Max Activating Token Index: 50

Text #4

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.2131. Min Act: -0.1700

Data Index: 1020487 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.1563. Min Act: -0.1700

Data Index: 3287420 (Open Web Text)

Max Activating Token Index: 14

Text #6

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.1479. Min Act: -0.1700

Data Index: 1379632 (Open Web Text)

Max Activating Token Index: 12

Text #7

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.1408. Min Act: -0.1700

Data Index: 1065911 (Open Web Text)

Max Activating Token Index: 16

Text #8

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.1375. Min Act: -0.1700

Data Index: 725599 (Open Web Text)

Max Activating Token Index: 419

Text #9

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.1002. Min Act: -0.1700

Data Index: 6742813 (Open Web Text)

Max Activating Token Index: 277

Text #10

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.1171. Min Act: -0.1700

Data Index: 7435545 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.1130. Min Act: -0.1700

Data Index: 8557768 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.1117. Min Act: -0.1700

Data Index: 3149946 (Open Web Text)

Max Activating Token Index: 173

Text #13

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.0947. Min Act: -0.1700

Data Index: 744563 (Open Web Text)

Max Activating Token Index: 39

Text #14

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.0936. Min Act: -0.1700

Data Index: 2124379 (Open Web Text)

Max Activating Token Index: 17

Text #15

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.1054. Min Act: -0.1700

Data Index: 6478759 (Open Web Text)

Max Activating Token Index: 23

Text #16

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.0954. Min Act: -0.1700

Data Index: 3704909 (Open Web Text)

Max Activating Token Index: 303

Text #17

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.0890. Min Act: -0.1700

Data Index: 5424578 (Open Web Text)

Max Activating Token Index: 18

Text #18

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.0904. Min Act: -0.1700

Data Index: 291460 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 3.2631. Min Range: -3.2631

Max Act: 3.0769. Min Act: -0.1700

Data Index: 7510787 (Open Web Text)

Max Activating Token Index: 21