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

Dataset: Open Web Text

Neuron 3045 in Layer 6

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: 6.8482. Min Range: -6.8482

Max Act: 6.8482. Min Act: -0.1700

Data Index: 7857336 (Open Web Text)

Max Activating Token Index: 321

Text #1

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.7300. Min Act: -0.1700

Data Index: 5092195 (Open Web Text)

Max Activating Token Index: 230

Text #2

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.6850. Min Act: -0.1700

Data Index: 3177651 (Open Web Text)

Max Activating Token Index: 375

Text #3

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.6929. Min Act: -0.1700

Data Index: 3646350 (Open Web Text)

Max Activating Token Index: 724

Text #4

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.6734. Min Act: -0.1700

Data Index: 1143148 (Open Web Text)

Max Activating Token Index: 757

Text #5

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.5853. Min Act: -0.1700

Data Index: 8418966 (Open Web Text)

Max Activating Token Index: 607

Text #6

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.6344. Min Act: -0.1700

Data Index: 563480 (Open Web Text)

Max Activating Token Index: 124

Text #7

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.5781. Min Act: -0.1700

Data Index: 7880539 (Open Web Text)

Max Activating Token Index: 796

Text #8

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.5773. Min Act: -0.1700

Data Index: 783930 (Open Web Text)

Max Activating Token Index: 259

Text #9

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.5201. Min Act: -0.1700

Data Index: 2267215 (Open Web Text)

Max Activating Token Index: 329

Text #10

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.5360. Min Act: -0.1700

Data Index: 7355650 (Open Web Text)

Max Activating Token Index: 580

Text #11

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.6119. Min Act: -0.1700

Data Index: 5482416 (Open Web Text)

Max Activating Token Index: 880

Text #12

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.6169. Min Act: -0.1700

Data Index: 5352482 (Open Web Text)

Max Activating Token Index: 916

Text #13

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.5496. Min Act: -0.1700

Data Index: 625851 (Open Web Text)

Max Activating Token Index: 941

Text #14

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.4225. Min Act: -0.1700

Data Index: 367949 (Open Web Text)

Max Activating Token Index: 1002

Text #15

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.5309. Min Act: -0.1700

Data Index: 4164140 (Open Web Text)

Max Activating Token Index: 962

Text #16

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.4770. Min Act: -0.1700

Data Index: 7017915 (Open Web Text)

Max Activating Token Index: 309

Text #17

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.4939. Min Act: -0.1700

Data Index: 6987006 (Open Web Text)

Max Activating Token Index: 982

Text #18

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.4338. Min Act: -0.1700

Data Index: 6403484 (Open Web Text)

Max Activating Token Index: 991

Text #19

Max Range: 6.8482. Min Range: -6.8482

Max Act: 6.4661. Min Act: -0.1700

Data Index: 752124 (Open Web Text)

Max Activating Token Index: 659