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

Dataset: Open Web Text

Neuron 1653 in Layer 2

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: 1.9691. Min Range: -1.9691

Max Act: 1.9691. Min Act: -0.1700

Data Index: 4337281 (Open Web Text)

Max Activating Token Index: 932

Text #1

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.9176. Min Act: -0.1699

Data Index: 4199681 (Open Web Text)

Max Activating Token Index: 172

Text #2

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8979. Min Act: -0.1700

Data Index: 2562870 (Open Web Text)

Max Activating Token Index: 869

Text #3

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.9025. Min Act: -0.1697

Data Index: 7203912 (Open Web Text)

Max Activating Token Index: 552

Text #4

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8728. Min Act: -0.1700

Data Index: 245903 (Open Web Text)

Max Activating Token Index: 155

Text #5

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8657. Min Act: -0.1700

Data Index: 1740662 (Open Web Text)

Max Activating Token Index: 310

Text #6

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8749. Min Act: -0.1700

Data Index: 7594096 (Open Web Text)

Max Activating Token Index: 110

Text #7

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8400. Min Act: -0.1700

Data Index: 8804718 (Open Web Text)

Max Activating Token Index: 774

Text #8

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8478. Min Act: -0.1700

Data Index: 945607 (Open Web Text)

Max Activating Token Index: 467

Text #9

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8462. Min Act: -0.1700

Data Index: 6045652 (Open Web Text)

Max Activating Token Index: 656

Text #10

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8557. Min Act: -0.1700

Data Index: 2190314 (Open Web Text)

Max Activating Token Index: 308

Text #11

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8404. Min Act: -0.1700

Data Index: 4582170 (Open Web Text)

Max Activating Token Index: 561

Text #12

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8142. Min Act: -0.1700

Data Index: 6602654 (Open Web Text)

Max Activating Token Index: 16

Text #13

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8374. Min Act: -0.1700

Data Index: 4678655 (Open Web Text)

Max Activating Token Index: 183

Text #14

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8272. Min Act: -0.1700

Data Index: 7187487 (Open Web Text)

Max Activating Token Index: 238

Text #15

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8279. Min Act: -0.1700

Data Index: 3809307 (Open Web Text)

Max Activating Token Index: 951

Text #16

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8242. Min Act: -0.1700

Data Index: 2435048 (Open Web Text)

Max Activating Token Index: 903

Text #17

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8034. Min Act: -0.1700

Data Index: 4856263 (Open Web Text)

Max Activating Token Index: 708

Text #18

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8200. Min Act: -0.1700

Data Index: 3407827 (Open Web Text)

Max Activating Token Index: 236

Text #19

Max Range: 1.9691. Min Range: -1.9691

Max Act: 1.8136. Min Act: -0.1697

Data Index: 1006148 (Open Web Text)

Max Activating Token Index: 323