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

Dataset: Open Web Text

Neuron 2898 in Layer 0

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: 11.4391. Min Range: -11.4391

Max Act: 11.4391. Min Act: -0.1700

Data Index: 5565494 (Open Web Text)

Max Activating Token Index: 769

Text #1

Max Range: 11.4391. Min Range: -11.4391

Max Act: 10.3045. Min Act: -0.1700

Data Index: 3292182 (Open Web Text)

Max Activating Token Index: 718

Text #2

Max Range: 11.4391. Min Range: -11.4391

Max Act: 10.3945. Min Act: -0.1700

Data Index: 1014877 (Open Web Text)

Max Activating Token Index: 735

Text #3

Max Range: 11.4391. Min Range: -11.4391

Max Act: 10.3029. Min Act: -0.1700

Data Index: 6854718 (Open Web Text)

Max Activating Token Index: 688

Text #4

Max Range: 11.4391. Min Range: -11.4391

Max Act: 10.1265. Min Act: -0.1700

Data Index: 560687 (Open Web Text)

Max Activating Token Index: 706

Text #5

Max Range: 11.4391. Min Range: -11.4391

Max Act: 10.0601. Min Act: -0.1700

Data Index: 5387427 (Open Web Text)

Max Activating Token Index: 764

Text #6

Max Range: 11.4391. Min Range: -11.4391

Max Act: 9.8408. Min Act: -0.1700

Data Index: 558502 (Open Web Text)

Max Activating Token Index: 678

Text #7

Max Range: 11.4391. Min Range: -11.4391

Max Act: 9.7520. Min Act: -0.1700

Data Index: 4918108 (Open Web Text)

Max Activating Token Index: 699

Text #8

Max Range: 11.4391. Min Range: -11.4391

Max Act: 9.7442. Min Act: -0.1700

Data Index: 4304943 (Open Web Text)

Max Activating Token Index: 659

Text #9

Max Range: 11.4391. Min Range: -11.4391

Max Act: 9.7123. Min Act: -0.1700

Data Index: 1539470 (Open Web Text)

Max Activating Token Index: 668

Text #10

Max Range: 11.4391. Min Range: -11.4391

Max Act: 9.6724. Min Act: -0.1700

Data Index: 5645715 (Open Web Text)

Max Activating Token Index: 728

Text #11

Max Range: 11.4391. Min Range: -11.4391

Max Act: 9.5907. Min Act: -0.1700

Data Index: 4251403 (Open Web Text)

Max Activating Token Index: 678

Text #12

Max Range: 11.4391. Min Range: -11.4391

Max Act: 9.6489. Min Act: -0.1700

Data Index: 3310593 (Open Web Text)

Max Activating Token Index: 758

Text #13

Max Range: 11.4391. Min Range: -11.4391

Max Act: 9.7195. Min Act: -0.1700

Data Index: 5829889 (Open Web Text)

Max Activating Token Index: 640

Text #14

Max Range: 11.4391. Min Range: -11.4391

Max Act: 9.4115. Min Act: -0.1700

Data Index: 6395877 (Open Web Text)

Max Activating Token Index: 668

Text #15

Max Range: 11.4391. Min Range: -11.4391

Max Act: 9.5452. Min Act: -0.1700

Data Index: 6061806 (Open Web Text)

Max Activating Token Index: 737

Text #16

Max Range: 11.4391. Min Range: -11.4391

Max Act: 9.5600. Min Act: -0.1700

Data Index: 2678035 (Open Web Text)

Max Activating Token Index: 742

Text #17

Max Range: 11.4391. Min Range: -11.4391

Max Act: 9.4679. Min Act: -0.1700

Data Index: 3793196 (Open Web Text)

Max Activating Token Index: 730

Text #18

Max Range: 11.4391. Min Range: -11.4391

Max Act: 9.5191. Min Act: -0.1700

Data Index: 6555069 (Open Web Text)

Max Activating Token Index: 715

Text #19

Max Range: 11.4391. Min Range: -11.4391

Max Act: 9.4711. Min Act: -0.1700

Data Index: 2591451 (Open Web Text)

Max Activating Token Index: 147