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

Dataset: Open Web Text

Neuron 700 in Layer 5

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: 4.6448. Min Range: -4.6448

Max Act: 4.6448. Min Act: -0.1700

Data Index: 2029138 (Open Web Text)

Max Activating Token Index: 188

Text #1

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.5812. Min Act: -0.1700

Data Index: 2508634 (Open Web Text)

Max Activating Token Index: 13

Text #2

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.5813. Min Act: -0.1700

Data Index: 2754923 (Open Web Text)

Max Activating Token Index: 17

Text #3

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.5203. Min Act: -0.1700

Data Index: 6732261 (Open Web Text)

Max Activating Token Index: 929

Text #4

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.5397. Min Act: -0.1700

Data Index: 7203003 (Open Web Text)

Max Activating Token Index: 325

Text #5

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.4900. Min Act: -0.1700

Data Index: 2603854 (Open Web Text)

Max Activating Token Index: 640

Text #6

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.4804. Min Act: -0.1700

Data Index: 1190841 (Open Web Text)

Max Activating Token Index: 365

Text #7

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.4908. Min Act: -0.1700

Data Index: 5476623 (Open Web Text)

Max Activating Token Index: 123

Text #8

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.4908. Min Act: -0.1700

Data Index: 1169368 (Open Web Text)

Max Activating Token Index: 1013

Text #9

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.4344. Min Act: -0.1700

Data Index: 6698257 (Open Web Text)

Max Activating Token Index: 599

Text #10

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.4802. Min Act: -0.1700

Data Index: 3555750 (Open Web Text)

Max Activating Token Index: 649

Text #11

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.4381. Min Act: -0.1700

Data Index: 1190840 (Open Web Text)

Max Activating Token Index: 521

Text #12

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.4624. Min Act: -0.1700

Data Index: 924712 (Open Web Text)

Max Activating Token Index: 955

Text #13

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.4548. Min Act: -0.1700

Data Index: 2780848 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.4538. Min Act: -0.1700

Data Index: 1540124 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.4102. Min Act: -0.1700

Data Index: 795320 (Open Web Text)

Max Activating Token Index: 462

Text #16

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.4065. Min Act: -0.1700

Data Index: 2715559 (Open Web Text)

Max Activating Token Index: 781

Text #17

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.4293. Min Act: -0.1700

Data Index: 2177892 (Open Web Text)

Max Activating Token Index: 584

Text #18

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.4379. Min Act: -0.1700

Data Index: 4107009 (Open Web Text)

Max Activating Token Index: 261

Text #19

Max Range: 4.6448. Min Range: -4.6448

Max Act: 4.4251. Min Act: -0.1700

Data Index: 617180 (Open Web Text)

Max Activating Token Index: 181