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

Dataset: Open Web Text

Neuron 1912 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: 1.6465. Min Range: -1.6465

Max Act: 1.6465. Min Act: -0.1693

Data Index: 4529760 (Open Web Text)

Max Activating Token Index: 370

Text #1

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.6070. Min Act: -0.1700

Data Index: 4553861 (Open Web Text)

Max Activating Token Index: 35

Text #2

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.6022. Min Act: -0.1693

Data Index: 6064150 (Open Web Text)

Max Activating Token Index: 51

Text #3

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.6080. Min Act: -0.1700

Data Index: 2137701 (Open Web Text)

Max Activating Token Index: 496

Text #4

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.5969. Min Act: -0.1693

Data Index: 3227615 (Open Web Text)

Max Activating Token Index: 170

Text #5

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.5938. Min Act: -0.1700

Data Index: 1901391 (Open Web Text)

Max Activating Token Index: 292

Text #6

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.5770. Min Act: -0.1700

Data Index: 7755736 (Open Web Text)

Max Activating Token Index: 970

Text #7

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.5879. Min Act: -0.1700

Data Index: 2008231 (Open Web Text)

Max Activating Token Index: 726

Text #8

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.5686. Min Act: -0.1700

Data Index: 1667062 (Open Web Text)

Max Activating Token Index: 343

Text #9

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.5566. Min Act: -0.1700

Data Index: 5413695 (Open Web Text)

Max Activating Token Index: 334

Text #10

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.5429. Min Act: -0.1699

Data Index: 4712753 (Open Web Text)

Max Activating Token Index: 254

Text #11

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.5459. Min Act: -0.1700

Data Index: 5683105 (Open Web Text)

Max Activating Token Index: 553

Text #12

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.5258. Min Act: -0.1693

Data Index: 4489945 (Open Web Text)

Max Activating Token Index: 408

Text #13

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.5165. Min Act: -0.1693

Data Index: 761041 (Open Web Text)

Max Activating Token Index: 131

Text #14

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.5121. Min Act: -0.1700

Data Index: 7855942 (Open Web Text)

Max Activating Token Index: 797

Text #15

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.5109. Min Act: -0.1700

Data Index: 7334682 (Open Web Text)

Max Activating Token Index: 46

Text #16

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.5034. Min Act: -0.1695

Data Index: 5298016 (Open Web Text)

Max Activating Token Index: 424

Text #17

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.4999. Min Act: -0.1693

Data Index: 3911370 (Open Web Text)

Max Activating Token Index: 71

Text #18

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.4835. Min Act: -0.1700

Data Index: 2669656 (Open Web Text)

Max Activating Token Index: 132

Text #19

Max Range: 1.6465. Min Range: -1.6465

Max Act: 1.4875. Min Act: -0.1700

Data Index: 1075447 (Open Web Text)

Max Activating Token Index: 206