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

Dataset: Open Web Text

Neuron 545 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: 4.8813. Min Range: -4.8813

Max Act: 4.8657. Min Act: -0.1700

Data Index: 1451801 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.8813. Min Act: -0.1700

Data Index: 3136346 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.8455. Min Act: -0.1700

Data Index: 3772288 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.8218. Min Act: -0.1700

Data Index: 8248188 (Open Web Text)

Max Activating Token Index: 460

Text #4

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.8137. Min Act: -0.1700

Data Index: 8230968 (Open Web Text)

Max Activating Token Index: 131

Text #5

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.8274. Min Act: -0.1699

Data Index: 6195930 (Open Web Text)

Max Activating Token Index: 37

Text #6

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.7581. Min Act: -0.1700

Data Index: 5446901 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.7598. Min Act: -0.1700

Data Index: 7044182 (Open Web Text)

Max Activating Token Index: 93

Text #8

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.7621. Min Act: -0.1700

Data Index: 3671382 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.7136. Min Act: -0.1700

Data Index: 3692559 (Open Web Text)

Max Activating Token Index: 39

Text #10

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.7088. Min Act: -0.1700

Data Index: 90342 (Open Web Text)

Max Activating Token Index: 734

Text #11

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.7138. Min Act: -0.1700

Data Index: 6680264 (Open Web Text)

Max Activating Token Index: 39

Text #12

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.7290. Min Act: -0.1700

Data Index: 4736031 (Open Web Text)

Max Activating Token Index: 92

Text #13

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.7300. Min Act: -0.1700

Data Index: 6562221 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.7223. Min Act: -0.1700

Data Index: 7679713 (Open Web Text)

Max Activating Token Index: 190

Text #15

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.7254. Min Act: -0.1700

Data Index: 815333 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.7172. Min Act: -0.1700

Data Index: 3475710 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.7255. Min Act: -0.1700

Data Index: 4814192 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.7297. Min Act: -0.1700

Data Index: 641795 (Open Web Text)

Max Activating Token Index: 318

Text #19

Max Range: 4.8813. Min Range: -4.8813

Max Act: 4.7281. Min Act: -0.1700

Data Index: 1239252 (Open Web Text)

Max Activating Token Index: 42