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

Dataset: Open Web Text

Neuron 871 in Layer 1

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: 2.3863. Min Range: -2.3863

Max Act: 2.3863. Min Act: -0.1700

Data Index: 5446135 (Open Web Text)

Max Activating Token Index: 1004

Text #1

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.3414. Min Act: -0.1700

Data Index: 1547154 (Open Web Text)

Max Activating Token Index: 802

Text #2

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.2894. Min Act: -0.1700

Data Index: 8798148 (Open Web Text)

Max Activating Token Index: 1001

Text #3

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.2453. Min Act: -0.1700

Data Index: 1747655 (Open Web Text)

Max Activating Token Index: 986

Text #4

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.1968. Min Act: -0.1700

Data Index: 3583648 (Open Web Text)

Max Activating Token Index: 993

Text #5

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.2036. Min Act: -0.1700

Data Index: 3615171 (Open Web Text)

Max Activating Token Index: 998

Text #6

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.2132. Min Act: -0.1700

Data Index: 7372940 (Open Web Text)

Max Activating Token Index: 1015

Text #7

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.1825. Min Act: -0.1700

Data Index: 392886 (Open Web Text)

Max Activating Token Index: 986

Text #8

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.1862. Min Act: -0.1700

Data Index: 5631849 (Open Web Text)

Max Activating Token Index: 994

Text #9

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.1451. Min Act: -0.1700

Data Index: 8745202 (Open Web Text)

Max Activating Token Index: 1012

Text #10

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.1425. Min Act: -0.1700

Data Index: 398886 (Open Web Text)

Max Activating Token Index: 996

Text #11

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.1618. Min Act: -0.1700

Data Index: 5614235 (Open Web Text)

Max Activating Token Index: 1001

Text #12

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.1507. Min Act: -0.1700

Data Index: 6621141 (Open Web Text)

Max Activating Token Index: 979

Text #13

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.1604. Min Act: -0.1700

Data Index: 2971606 (Open Web Text)

Max Activating Token Index: 992

Text #14

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.1443. Min Act: -0.1700

Data Index: 7957868 (Open Web Text)

Max Activating Token Index: 944

Text #15

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.1410. Min Act: -0.1700

Data Index: 5566894 (Open Web Text)

Max Activating Token Index: 996

Text #16

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.1229. Min Act: -0.1700

Data Index: 5856329 (Open Web Text)

Max Activating Token Index: 972

Text #17

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.1105. Min Act: -0.1700

Data Index: 2394657 (Open Web Text)

Max Activating Token Index: 1006

Text #18

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.1314. Min Act: -0.1700

Data Index: 7773632 (Open Web Text)

Max Activating Token Index: 967

Text #19

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.1478. Min Act: -0.1700

Data Index: 4448077 (Open Web Text)

Max Activating Token Index: 994