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

Dataset: Open Web Text

Neuron 1710 in Layer 4

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: 3.3968. Min Range: -3.3968

Max Act: 3.3968. Min Act: -0.1700

Data Index: 8387442 (Open Web Text)

Max Activating Token Index: 82

Text #1

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3808. Min Act: -0.1700

Data Index: 4981329 (Open Web Text)

Max Activating Token Index: 130

Text #2

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3469. Min Act: -0.1700

Data Index: 7456737 (Open Web Text)

Max Activating Token Index: 906

Text #3

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3109. Min Act: -0.1700

Data Index: 170846 (Open Web Text)

Max Activating Token Index: 829

Text #4

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.3244. Min Act: -0.1700

Data Index: 6636786 (Open Web Text)

Max Activating Token Index: 44

Text #5

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2626. Min Act: -0.1700

Data Index: 3471875 (Open Web Text)

Max Activating Token Index: 952

Text #6

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2634. Min Act: -0.1700

Data Index: 8701918 (Open Web Text)

Max Activating Token Index: 998

Text #7

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2596. Min Act: -0.1700

Data Index: 5023804 (Open Web Text)

Max Activating Token Index: 271

Text #8

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2751. Min Act: -0.1700

Data Index: 5767478 (Open Web Text)

Max Activating Token Index: 12

Text #9

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2269. Min Act: -0.1700

Data Index: 3329046 (Open Web Text)

Max Activating Token Index: 146

Text #10

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2187. Min Act: -0.1700

Data Index: 4390989 (Open Web Text)

Max Activating Token Index: 60

Text #11

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2344. Min Act: -0.1700

Data Index: 8607397 (Open Web Text)

Max Activating Token Index: 854

Text #12

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2003. Min Act: -0.1700

Data Index: 2721045 (Open Web Text)

Max Activating Token Index: 38

Text #13

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2007. Min Act: -0.1700

Data Index: 2348934 (Open Web Text)

Max Activating Token Index: 400

Text #14

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2198. Min Act: -0.1700

Data Index: 2266595 (Open Web Text)

Max Activating Token Index: 640

Text #15

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2030. Min Act: -0.1700

Data Index: 1074303 (Open Web Text)

Max Activating Token Index: 29

Text #16

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.1988. Min Act: -0.1700

Data Index: 5892635 (Open Web Text)

Max Activating Token Index: 36

Text #17

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.2240. Min Act: -0.1700

Data Index: 4315308 (Open Web Text)

Max Activating Token Index: 831

Text #18

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.1586. Min Act: -0.1700

Data Index: 6548043 (Open Web Text)

Max Activating Token Index: 458

Text #19

Max Range: 3.3968. Min Range: -3.3968

Max Act: 3.1802. Min Act: -0.1700

Data Index: 3800620 (Open Web Text)

Max Activating Token Index: 63