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

Dataset: Open Web Text

Neuron 2773 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: 4.3756. Min Range: -4.3756

Max Act: 4.3756. Min Act: -0.1700

Data Index: 3114025 (Open Web Text)

Max Activating Token Index: 165

Text #1

Max Range: 4.3756. Min Range: -4.3756

Max Act: 4.1669. Min Act: -0.1700

Data Index: 3264707 (Open Web Text)

Max Activating Token Index: 202

Text #2

Max Range: 4.3756. Min Range: -4.3756

Max Act: 4.1289. Min Act: -0.1700

Data Index: 7151216 (Open Web Text)

Max Activating Token Index: 741

Text #3

Max Range: 4.3756. Min Range: -4.3756

Max Act: 4.0867. Min Act: -0.1700

Data Index: 1933721 (Open Web Text)

Max Activating Token Index: 533

Text #4

Max Range: 4.3756. Min Range: -4.3756

Max Act: 4.0507. Min Act: -0.1700

Data Index: 2553769 (Open Web Text)

Max Activating Token Index: 695

Text #5

Max Range: 4.3756. Min Range: -4.3756

Max Act: 4.0838. Min Act: -0.1700

Data Index: 1708291 (Open Web Text)

Max Activating Token Index: 226

Text #6

Max Range: 4.3756. Min Range: -4.3756

Max Act: 3.9868. Min Act: -0.1700

Data Index: 4696657 (Open Web Text)

Max Activating Token Index: 918

Text #7

Max Range: 4.3756. Min Range: -4.3756

Max Act: 4.0451. Min Act: -0.1700

Data Index: 2234637 (Open Web Text)

Max Activating Token Index: 527

Text #8

Max Range: 4.3756. Min Range: -4.3756

Max Act: 4.0176. Min Act: -0.1700

Data Index: 7652461 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 4.3756. Min Range: -4.3756

Max Act: 3.9993. Min Act: -0.1700

Data Index: 1283660 (Open Web Text)

Max Activating Token Index: 126

Text #10

Max Range: 4.3756. Min Range: -4.3756

Max Act: 3.9661. Min Act: -0.1700

Data Index: 8364986 (Open Web Text)

Max Activating Token Index: 646

Text #11

Max Range: 4.3756. Min Range: -4.3756

Max Act: 3.9569. Min Act: -0.1700

Data Index: 5276083 (Open Web Text)

Max Activating Token Index: 995

Text #12

Max Range: 4.3756. Min Range: -4.3756

Max Act: 3.9867. Min Act: -0.1700

Data Index: 482369 (Open Web Text)

Max Activating Token Index: 118

Text #13

Max Range: 4.3756. Min Range: -4.3756

Max Act: 3.9794. Min Act: -0.1700

Data Index: 416916 (Open Web Text)

Max Activating Token Index: 473

Text #14

Max Range: 4.3756. Min Range: -4.3756

Max Act: 3.9172. Min Act: -0.1700

Data Index: 3576759 (Open Web Text)

Max Activating Token Index: 637

Text #15

Max Range: 4.3756. Min Range: -4.3756

Max Act: 3.9716. Min Act: -0.1700

Data Index: 3426872 (Open Web Text)

Max Activating Token Index: 436

Text #16

Max Range: 4.3756. Min Range: -4.3756

Max Act: 3.9036. Min Act: -0.1700

Data Index: 3415589 (Open Web Text)

Max Activating Token Index: 991

Text #17

Max Range: 4.3756. Min Range: -4.3756

Max Act: 3.9435. Min Act: -0.1700

Data Index: 486395 (Open Web Text)

Max Activating Token Index: 532

Text #18

Max Range: 4.3756. Min Range: -4.3756

Max Act: 3.9318. Min Act: -0.1700

Data Index: 2162924 (Open Web Text)

Max Activating Token Index: 346

Text #19

Max Range: 4.3756. Min Range: -4.3756

Max Act: 3.9147. Min Act: -0.1700

Data Index: 252217 (Open Web Text)

Max Activating Token Index: 366