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

Dataset: Open Web Text

Neuron 350 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: 3.2743. Min Range: -3.2743

Max Act: 3.2743. Min Act: -0.1700

Data Index: 5716416 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2448. Min Act: -0.1700

Data Index: 1213731 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2351. Min Act: -0.1700

Data Index: 5460623 (Open Web Text)

Max Activating Token Index: 631

Text #3

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2438. Min Act: -0.1700

Data Index: 7107700 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2286. Min Act: -0.1700

Data Index: 1063116 (Open Web Text)

Max Activating Token Index: 548

Text #5

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2264. Min Act: -0.1700

Data Index: 7219013 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2212. Min Act: -0.1700

Data Index: 887122 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2054. Min Act: -0.1700

Data Index: 4846127 (Open Web Text)

Max Activating Token Index: 8

Text #8

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2181. Min Act: -0.1700

Data Index: 3781391 (Open Web Text)

Max Activating Token Index: 16

Text #9

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2112. Min Act: -0.1700

Data Index: 7652563 (Open Web Text)

Max Activating Token Index: 474

Text #10

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2209. Min Act: -0.1700

Data Index: 2284036 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2121. Min Act: -0.1700

Data Index: 2869961 (Open Web Text)

Max Activating Token Index: 979

Text #12

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1901. Min Act: -0.1700

Data Index: 948009 (Open Web Text)

Max Activating Token Index: 8

Text #13

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2011. Min Act: -0.1700

Data Index: 8282380 (Open Web Text)

Max Activating Token Index: 5

Text #14

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2079. Min Act: -0.1700

Data Index: 1658710 (Open Web Text)

Max Activating Token Index: 937

Text #15

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2066. Min Act: -0.1700

Data Index: 7236343 (Open Web Text)

Max Activating Token Index: 436

Text #16

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1970. Min Act: -0.1700

Data Index: 7546161 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.2086. Min Act: -0.1700

Data Index: 4886939 (Open Web Text)

Max Activating Token Index: 15

Text #18

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1816. Min Act: -0.1700

Data Index: 3886308 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 3.2743. Min Range: -3.2743

Max Act: 3.1839. Min Act: -0.1700

Data Index: 4088133 (Open Web Text)

Max Activating Token Index: 536