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

Dataset: Open Web Text

Neuron 763 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: 4.1286. Min Range: -4.1286

Max Act: 4.1286. Min Act: -0.1700

Data Index: 7359009 (Open Web Text)

Max Activating Token Index: 11

Text #1

Max Range: 4.1286. Min Range: -4.1286

Max Act: 4.0960. Min Act: -0.1700

Data Index: 6614756 (Open Web Text)

Max Activating Token Index: 801

Text #2

Max Range: 4.1286. Min Range: -4.1286

Max Act: 4.0281. Min Act: -0.1700

Data Index: 2685904 (Open Web Text)

Max Activating Token Index: 373

Text #3

Max Range: 4.1286. Min Range: -4.1286

Max Act: 4.0235. Min Act: -0.1700

Data Index: 331724 (Open Web Text)

Max Activating Token Index: 704

Text #4

Max Range: 4.1286. Min Range: -4.1286

Max Act: 4.0092. Min Act: -0.1700

Data Index: 3704161 (Open Web Text)

Max Activating Token Index: 27

Text #5

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9823. Min Act: -0.1700

Data Index: 3772917 (Open Web Text)

Max Activating Token Index: 32

Text #6

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9641. Min Act: -0.1700

Data Index: 3185932 (Open Web Text)

Max Activating Token Index: 16

Text #7

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9461. Min Act: -0.1700

Data Index: 6246460 (Open Web Text)

Max Activating Token Index: 615

Text #8

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9469. Min Act: -0.1700

Data Index: 7654850 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9340. Min Act: -0.1700

Data Index: 7640035 (Open Web Text)

Max Activating Token Index: 22

Text #10

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9310. Min Act: -0.1700

Data Index: 33881 (Open Web Text)

Max Activating Token Index: 21

Text #11

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9456. Min Act: -0.1700

Data Index: 7404860 (Open Web Text)

Max Activating Token Index: 72

Text #12

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9438. Min Act: -0.1700

Data Index: 5767872 (Open Web Text)

Max Activating Token Index: 19

Text #13

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9336. Min Act: -0.1700

Data Index: 384484 (Open Web Text)

Max Activating Token Index: 16

Text #14

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9036. Min Act: -0.1700

Data Index: 6305610 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9401. Min Act: -0.1700

Data Index: 5711757 (Open Web Text)

Max Activating Token Index: 422

Text #16

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9038. Min Act: -0.1700

Data Index: 4249672 (Open Web Text)

Max Activating Token Index: 138

Text #17

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.9309. Min Act: -0.1700

Data Index: 7021870 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.8862. Min Act: -0.1700

Data Index: 839647 (Open Web Text)

Max Activating Token Index: 773

Text #19

Max Range: 4.1286. Min Range: -4.1286

Max Act: 3.8964. Min Act: -0.1700

Data Index: 1941272 (Open Web Text)

Max Activating Token Index: 69