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

Dataset: Open Web Text

Neuron 2400 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: 4.5187. Min Range: -4.5187

Max Act: 4.5187. Min Act: -0.1700

Data Index: 6603663 (Open Web Text)

Max Activating Token Index: 834

Text #1

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.4793. Min Act: -0.1700

Data Index: 5478682 (Open Web Text)

Max Activating Token Index: 702

Text #2

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.4100. Min Act: -0.1700

Data Index: 8358581 (Open Web Text)

Max Activating Token Index: 811

Text #3

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.2827. Min Act: -0.1700

Data Index: 5772948 (Open Web Text)

Max Activating Token Index: 621

Text #4

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.2796. Min Act: -0.1700

Data Index: 6244184 (Open Web Text)

Max Activating Token Index: 341

Text #5

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.2561. Min Act: -0.1700

Data Index: 7493628 (Open Web Text)

Max Activating Token Index: 965

Text #6

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.2493. Min Act: -0.1700

Data Index: 1854785 (Open Web Text)

Max Activating Token Index: 1003

Text #7

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.2353. Min Act: -0.1700

Data Index: 2963683 (Open Web Text)

Max Activating Token Index: 479

Text #8

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.2176. Min Act: -0.1700

Data Index: 5270689 (Open Web Text)

Max Activating Token Index: 242

Text #9

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.2114. Min Act: -0.1700

Data Index: 1933795 (Open Web Text)

Max Activating Token Index: 629

Text #10

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.2414. Min Act: -0.1700

Data Index: 4282542 (Open Web Text)

Max Activating Token Index: 258

Text #11

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.1683. Min Act: -0.1700

Data Index: 8329136 (Open Web Text)

Max Activating Token Index: 426

Text #12

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.1596. Min Act: -0.1700

Data Index: 8357297 (Open Web Text)

Max Activating Token Index: 718

Text #13

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.1569. Min Act: -0.1700

Data Index: 3525392 (Open Web Text)

Max Activating Token Index: 368

Text #14

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.1079. Min Act: -0.1700

Data Index: 3309941 (Open Web Text)

Max Activating Token Index: 866

Text #15

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.1161. Min Act: -0.1700

Data Index: 4105785 (Open Web Text)

Max Activating Token Index: 177

Text #16

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.1202. Min Act: -0.1700

Data Index: 6000976 (Open Web Text)

Max Activating Token Index: 691

Text #17

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.0785. Min Act: -0.1700

Data Index: 6021818 (Open Web Text)

Max Activating Token Index: 159

Text #18

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.0532. Min Act: -0.1700

Data Index: 3549345 (Open Web Text)

Max Activating Token Index: 638

Text #19

Max Range: 4.5187. Min Range: -4.5187

Max Act: 4.0056. Min Act: -0.1700

Data Index: 6251607 (Open Web Text)

Max Activating Token Index: 170