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

Dataset: Open Web Text

Neuron 1516 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: 5.3765. Min Range: -5.3765

Max Act: 5.3765. Min Act: -0.1700

Data Index: 6635370 (Open Web Text)

Max Activating Token Index: 157

Text #1

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.3565. Min Act: -0.1700

Data Index: 1385018 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.3040. Min Act: -0.1700

Data Index: 7136937 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.2975. Min Act: -0.1700

Data Index: 2399290 (Open Web Text)

Max Activating Token Index: 793

Text #4

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.3079. Min Act: -0.1700

Data Index: 8700609 (Open Web Text)

Max Activating Token Index: 711

Text #5

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.3014. Min Act: -0.1700

Data Index: 3739975 (Open Web Text)

Max Activating Token Index: 993

Text #6

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.2674. Min Act: -0.1700

Data Index: 160695 (Open Web Text)

Max Activating Token Index: 1020

Text #7

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.2558. Min Act: -0.1700

Data Index: 2245781 (Open Web Text)

Max Activating Token Index: 143

Text #8

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.2339. Min Act: -0.1700

Data Index: 842263 (Open Web Text)

Max Activating Token Index: 227

Text #9

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.2290. Min Act: -0.1700

Data Index: 5707927 (Open Web Text)

Max Activating Token Index: 25

Text #10

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.2160. Min Act: -0.1700

Data Index: 1240636 (Open Web Text)

Max Activating Token Index: 742

Text #11

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.2229. Min Act: -0.1700

Data Index: 3218010 (Open Web Text)

Max Activating Token Index: 897

Text #12

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.2564. Min Act: -0.1699

Data Index: 8109562 (Open Web Text)

Max Activating Token Index: 13

Text #13

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.2529. Min Act: -0.1698

Data Index: 7703028 (Open Web Text)

Max Activating Token Index: 586

Text #14

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.2407. Min Act: -0.1700

Data Index: 1982803 (Open Web Text)

Max Activating Token Index: 114

Text #15

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.2196. Min Act: -0.1700

Data Index: 5076099 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.1810. Min Act: -0.1700

Data Index: 778307 (Open Web Text)

Max Activating Token Index: 922

Text #17

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.2094. Min Act: -0.1698

Data Index: 5739450 (Open Web Text)

Max Activating Token Index: 1004

Text #18

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.2148. Min Act: -0.1700

Data Index: 6162209 (Open Web Text)

Max Activating Token Index: 182

Text #19

Max Range: 5.3765. Min Range: -5.3765

Max Act: 5.1919. Min Act: -0.1700

Data Index: 6332085 (Open Web Text)

Max Activating Token Index: 720