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

Dataset: Open Web Text

Neuron 2787 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: 1.7327. Min Range: -1.7327

Max Act: 1.7327. Min Act: -0.1700

Data Index: 3420960 (Open Web Text)

Max Activating Token Index: 671

Text #1

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.7042. Min Act: -0.1694

Data Index: 6048233 (Open Web Text)

Max Activating Token Index: 215

Text #2

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.6778. Min Act: -0.1700

Data Index: 4585674 (Open Web Text)

Max Activating Token Index: 845

Text #3

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.6358. Min Act: -0.1700

Data Index: 268578 (Open Web Text)

Max Activating Token Index: 194

Text #4

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.6453. Min Act: -0.1700

Data Index: 3789677 (Open Web Text)

Max Activating Token Index: 434

Text #5

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.6393. Min Act: -0.1687

Data Index: 3758237 (Open Web Text)

Max Activating Token Index: 188

Text #6

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.6364. Min Act: -0.1700

Data Index: 5833657 (Open Web Text)

Max Activating Token Index: 260

Text #7

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.6173. Min Act: -0.1684

Data Index: 2686176 (Open Web Text)

Max Activating Token Index: 891

Text #8

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.6330. Min Act: -0.1700

Data Index: 8637064 (Open Web Text)

Max Activating Token Index: 477

Text #9

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.6162. Min Act: -0.1700

Data Index: 809726 (Open Web Text)

Max Activating Token Index: 754

Text #10

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.6183. Min Act: -0.1700

Data Index: 5487202 (Open Web Text)

Max Activating Token Index: 978

Text #11

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.5935. Min Act: -0.1700

Data Index: 5180560 (Open Web Text)

Max Activating Token Index: 443

Text #12

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.6008. Min Act: -0.1700

Data Index: 5625666 (Open Web Text)

Max Activating Token Index: 830

Text #13

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.5967. Min Act: -0.1700

Data Index: 4621993 (Open Web Text)

Max Activating Token Index: 873

Text #14

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.6039. Min Act: -0.1700

Data Index: 312306 (Open Web Text)

Max Activating Token Index: 935

Text #15

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.5683. Min Act: -0.1700

Data Index: 2340697 (Open Web Text)

Max Activating Token Index: 662

Text #16

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.5889. Min Act: -0.1700

Data Index: 2314585 (Open Web Text)

Max Activating Token Index: 973

Text #17

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.6000. Min Act: -0.1700

Data Index: 5671154 (Open Web Text)

Max Activating Token Index: 874

Text #18

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.5893. Min Act: -0.1700

Data Index: 5463784 (Open Web Text)

Max Activating Token Index: 53

Text #19

Max Range: 1.7327. Min Range: -1.7327

Max Act: 1.5944. Min Act: -0.1699

Data Index: 3320408 (Open Web Text)

Max Activating Token Index: 642