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

Dataset: Open Web Text

Neuron 0 in Layer 3

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: 6.2221. Min Range: -6.2221

Max Act: 6.1839. Min Act: -0.1700

Data Index: 3348969 (Open Web Text)

Max Activating Token Index: 732

Text #1

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.2221. Min Act: -0.1700

Data Index: 6788150 (Open Web Text)

Max Activating Token Index: 734

Text #2

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.1532. Min Act: -0.1700

Data Index: 830901 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.1227. Min Act: -0.1700

Data Index: 206196 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.1061. Min Act: -0.1700

Data Index: 4936071 (Open Web Text)

Max Activating Token Index: 21

Text #5

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.0745. Min Act: -0.1700

Data Index: 1149255 (Open Web Text)

Max Activating Token Index: 494

Text #6

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.0846. Min Act: -0.1700

Data Index: 2099583 (Open Web Text)

Max Activating Token Index: 590

Text #7

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.0708. Min Act: -0.1700

Data Index: 980160 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.0708. Min Act: -0.1700

Data Index: 2071814 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.0708. Min Act: -0.1700

Data Index: 1371992 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.0708. Min Act: -0.1700

Data Index: 1858854 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.0708. Min Act: -0.1700

Data Index: 1301240 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.0708. Min Act: -0.1700

Data Index: 99305 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.0708. Min Act: -0.1700

Data Index: 586739 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.0708. Min Act: -0.1700

Data Index: 1278568 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.0708. Min Act: -0.1700

Data Index: 1715273 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.0528. Min Act: -0.1700

Data Index: 532657 (Open Web Text)

Max Activating Token Index: 34

Text #17

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.0708. Min Act: -0.1700

Data Index: 1377506 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.0708. Min Act: -0.1700

Data Index: 1373301 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 6.2221. Min Range: -6.2221

Max Act: 6.0708. Min Act: -0.1700

Data Index: 149831 (Open Web Text)

Max Activating Token Index: 2