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

Dataset: Open Web Text

Neuron 1145 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: 2.7916. Min Range: -2.7916

Max Act: 2.7916. Min Act: -0.1700

Data Index: 5408900 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.7465. Min Act: -0.1700

Data Index: 8405638 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.7527. Min Act: -0.1700

Data Index: 3149915 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.7465. Min Act: -0.1700

Data Index: 7550083 (Open Web Text)

Max Activating Token Index: 2

Text #4

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.7585. Min Act: -0.1700

Data Index: 5126801 (Open Web Text)

Max Activating Token Index: 33

Text #5

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.7330. Min Act: -0.1700

Data Index: 2849013 (Open Web Text)

Max Activating Token Index: 8

Text #6

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.7397. Min Act: -0.1700

Data Index: 2027759 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.7162. Min Act: -0.1700

Data Index: 4674121 (Open Web Text)

Max Activating Token Index: 7

Text #8

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.7220. Min Act: -0.1700

Data Index: 6990909 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.7265. Min Act: -0.1700

Data Index: 1408299 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.7220. Min Act: -0.1700

Data Index: 470868 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.7168. Min Act: -0.1700

Data Index: 8780973 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.7220. Min Act: -0.1700

Data Index: 5492996 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.7216. Min Act: -0.1700

Data Index: 8248558 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.7129. Min Act: -0.1700

Data Index: 2217081 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.7119. Min Act: -0.1700

Data Index: 2646458 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.7031. Min Act: -0.1700

Data Index: 7369991 (Open Web Text)

Max Activating Token Index: 16

Text #17

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.6928. Min Act: -0.1700

Data Index: 4375726 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.6906. Min Act: -0.1700

Data Index: 6979046 (Open Web Text)

Max Activating Token Index: 331

Text #19

Max Range: 2.7916. Min Range: -2.7916

Max Act: 2.6976. Min Act: -0.1700

Data Index: 7864559 (Open Web Text)

Max Activating Token Index: 657