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

Dataset: Open Web Text

Neuron 2072 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: 4.4087. Min Range: -4.4087

Max Act: 4.3973. Min Act: -0.1700

Data Index: 4375582 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.4087. Min Act: -0.1700

Data Index: 6297188 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.3641. Min Act: -0.1700

Data Index: 4639141 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2769. Min Act: -0.1700

Data Index: 2306143 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2725. Min Act: -0.1700

Data Index: 7433325 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2363. Min Act: -0.1700

Data Index: 7518346 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2536. Min Act: -0.1700

Data Index: 6777058 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2528. Min Act: -0.1700

Data Index: 435929 (Open Web Text)

Max Activating Token Index: 3

Text #8

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2390. Min Act: -0.1700

Data Index: 6352873 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2400. Min Act: -0.1700

Data Index: 3281219 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2659. Min Act: -0.1700

Data Index: 7405227 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2484. Min Act: -0.1700

Data Index: 7421660 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2253. Min Act: -0.1700

Data Index: 2725353 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2262. Min Act: -0.1700

Data Index: 3505224 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2227. Min Act: -0.1700

Data Index: 1972897 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2120. Min Act: -0.1700

Data Index: 1972899 (Open Web Text)

Max Activating Token Index: 5

Text #16

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2095. Min Act: -0.1700

Data Index: 7232629 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2235. Min Act: -0.1700

Data Index: 1143512 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2029. Min Act: -0.1700

Data Index: 4138954 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 4.4087. Min Range: -4.4087

Max Act: 4.2286. Min Act: -0.1700

Data Index: 249416 (Open Web Text)

Max Activating Token Index: 2