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

Dataset: Open Web Text

Neuron 221 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: 4.4570. Min Range: -4.4570

Max Act: 4.4570. Min Act: -0.1700

Data Index: 5338391 (Open Web Text)

Max Activating Token Index: 6

Text #1

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.3049. Min Act: -0.1700

Data Index: 3118652 (Open Web Text)

Max Activating Token Index: 19

Text #2

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.3107. Min Act: -0.1700

Data Index: 5140275 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.2120. Min Act: -0.1700

Data Index: 4062193 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.2319. Min Act: -0.1700

Data Index: 3060427 (Open Web Text)

Max Activating Token Index: 913

Text #5

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.2105. Min Act: -0.1700

Data Index: 1224536 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.2063. Min Act: -0.1700

Data Index: 2361591 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.2118. Min Act: -0.1700

Data Index: 2160287 (Open Web Text)

Max Activating Token Index: 15

Text #8

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.1923. Min Act: -0.1700

Data Index: 1414774 (Open Web Text)

Max Activating Token Index: 655

Text #9

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.2041. Min Act: -0.1700

Data Index: 4404635 (Open Web Text)

Max Activating Token Index: 9

Text #10

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.2021. Min Act: -0.1700

Data Index: 7146474 (Open Web Text)

Max Activating Token Index: 5

Text #11

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.2132. Min Act: -0.1700

Data Index: 6985166 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.2205. Min Act: -0.1700

Data Index: 6581039 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.1822. Min Act: -0.1700

Data Index: 5024027 (Open Web Text)

Max Activating Token Index: 21

Text #14

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.1851. Min Act: -0.1700

Data Index: 5699521 (Open Web Text)

Max Activating Token Index: 995

Text #15

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.1898. Min Act: -0.1700

Data Index: 6114551 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.1731. Min Act: -0.1700

Data Index: 2618326 (Open Web Text)

Max Activating Token Index: 518

Text #17

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.1940. Min Act: -0.1700

Data Index: 3317413 (Open Web Text)

Max Activating Token Index: 7

Text #18

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.1863. Min Act: -0.1700

Data Index: 3369057 (Open Web Text)

Max Activating Token Index: 612

Text #19

Max Range: 4.4570. Min Range: -4.4570

Max Act: 4.1724. Min Act: -0.1700

Data Index: 3775237 (Open Web Text)

Max Activating Token Index: 7