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

Dataset: Open Web Text

Neuron 11 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: 0.3390. Min Range: -0.3390

Max Act: 0.3390. Min Act: -0.1692

Data Index: 8421219 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.3336. Min Act: -0.1700

Data Index: 170018 (Open Web Text)

Max Activating Token Index: 5

Text #2

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2723. Min Act: -0.1658

Data Index: 4762928 (Open Web Text)

Max Activating Token Index: 12

Text #3

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2628. Min Act: -0.1671

Data Index: 3130148 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2429. Min Act: -0.1700

Data Index: 7710737 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2275. Min Act: -0.1698

Data Index: 8052686 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2291. Min Act: -0.1700

Data Index: 1244154 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2261. Min Act: -0.1700

Data Index: 8500122 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2188. Min Act: -0.1674

Data Index: 7487272 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2240. Min Act: -0.1700

Data Index: 2212322 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2179. Min Act: -0.1684

Data Index: 3229769 (Open Web Text)

Max Activating Token Index: 10

Text #11

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2222. Min Act: -0.1699

Data Index: 6005144 (Open Web Text)

Max Activating Token Index: 7

Text #12

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2137. Min Act: -0.1700

Data Index: 928778 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2094. Min Act: -0.1696

Data Index: 7648927 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2052. Min Act: -0.1699

Data Index: 2732004 (Open Web Text)

Max Activating Token Index: 1016

Text #15

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2077. Min Act: -0.1675

Data Index: 3488398 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2061. Min Act: -0.1699

Data Index: 3968218 (Open Web Text)

Max Activating Token Index: 3

Text #17

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2082. Min Act: -0.1700

Data Index: 8567119 (Open Web Text)

Max Activating Token Index: 5

Text #18

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.2048. Min Act: -0.1694

Data Index: 1443579 (Open Web Text)

Max Activating Token Index: 12

Text #19

Max Range: 0.3390. Min Range: -0.3390

Max Act: 0.1985. Min Act: -0.1696

Data Index: 6691359 (Open Web Text)

Max Activating Token Index: 8