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

Dataset: Open Web Text

Neuron 71 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: 3.5979. Min Range: -3.5979

Max Act: 3.5937. Min Act: -0.1700

Data Index: 3624501 (Open Web Text)

Max Activating Token Index: 33

Text #1

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.5979. Min Act: -0.1700

Data Index: 1346660 (Open Web Text)

Max Activating Token Index: 25

Text #2

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4990. Min Act: -0.1700

Data Index: 6928773 (Open Web Text)

Max Activating Token Index: 621

Text #3

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4949. Min Act: -0.1700

Data Index: 4020688 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4904. Min Act: -0.1700

Data Index: 5821000 (Open Web Text)

Max Activating Token Index: 43

Text #5

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4694. Min Act: -0.1700

Data Index: 1109676 (Open Web Text)

Max Activating Token Index: 520

Text #6

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4418. Min Act: -0.1700

Data Index: 225051 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4461. Min Act: -0.1700

Data Index: 1882116 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4547. Min Act: -0.1700

Data Index: 994172 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4475. Min Act: -0.1700

Data Index: 6707436 (Open Web Text)

Max Activating Token Index: 3

Text #10

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4300. Min Act: -0.1700

Data Index: 3087108 (Open Web Text)

Max Activating Token Index: 32

Text #11

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4327. Min Act: -0.1700

Data Index: 3633350 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4224. Min Act: -0.1700

Data Index: 5000375 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4413. Min Act: -0.1700

Data Index: 7902314 (Open Web Text)

Max Activating Token Index: 35

Text #14

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4320. Min Act: -0.1700

Data Index: 4315007 (Open Web Text)

Max Activating Token Index: 56

Text #15

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4297. Min Act: -0.1700

Data Index: 291591 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4311. Min Act: -0.1700

Data Index: 2156226 (Open Web Text)

Max Activating Token Index: 23

Text #17

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4118. Min Act: -0.1700

Data Index: 5070024 (Open Web Text)

Max Activating Token Index: 190

Text #18

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4202. Min Act: -0.1700

Data Index: 3206466 (Open Web Text)

Max Activating Token Index: 22

Text #19

Max Range: 3.5979. Min Range: -3.5979

Max Act: 3.4174. Min Act: -0.1700

Data Index: 6609360 (Open Web Text)

Max Activating Token Index: 47