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

Dataset: Open Web Text

Neuron 572 in Layer 3

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: 3.6436. Min Range: -3.6436

Max Act: 3.6396. Min Act: -0.1700

Data Index: 5719546 (Open Web Text)

Max Activating Token Index: 692

Text #1

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.6253. Min Act: -0.1700

Data Index: 7198140 (Open Web Text)

Max Activating Token Index: 958

Text #2

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.6436. Min Act: -0.1700

Data Index: 4192344 (Open Web Text)

Max Activating Token Index: 906

Text #3

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.6199. Min Act: -0.1700

Data Index: 5887718 (Open Web Text)

Max Activating Token Index: 15

Text #4

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.6036. Min Act: -0.1700

Data Index: 8735261 (Open Web Text)

Max Activating Token Index: 66

Text #5

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.5774. Min Act: -0.1700

Data Index: 8712385 (Open Web Text)

Max Activating Token Index: 696

Text #6

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.5827. Min Act: -0.1700

Data Index: 451178 (Open Web Text)

Max Activating Token Index: 477

Text #7

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.5120. Min Act: -0.1700

Data Index: 2914927 (Open Web Text)

Max Activating Token Index: 792

Text #8

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.5731. Min Act: -0.1700

Data Index: 2374974 (Open Web Text)

Max Activating Token Index: 613

Text #9

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.5441. Min Act: -0.1700

Data Index: 3070058 (Open Web Text)

Max Activating Token Index: 696

Text #10

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.5499. Min Act: -0.1700

Data Index: 1892373 (Open Web Text)

Max Activating Token Index: 727

Text #11

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.5480. Min Act: -0.1700

Data Index: 1410537 (Open Web Text)

Max Activating Token Index: 951

Text #12

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.5472. Min Act: -0.1700

Data Index: 5058270 (Open Web Text)

Max Activating Token Index: 123

Text #13

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.5529. Min Act: -0.1700

Data Index: 3769151 (Open Web Text)

Max Activating Token Index: 111

Text #14

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.5254. Min Act: -0.1700

Data Index: 7703031 (Open Web Text)

Max Activating Token Index: 931

Text #15

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.5467. Min Act: -0.1700

Data Index: 6403912 (Open Web Text)

Max Activating Token Index: 785

Text #16

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.5239. Min Act: -0.1700

Data Index: 8083754 (Open Web Text)

Max Activating Token Index: 668

Text #17

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.5487. Min Act: -0.1700

Data Index: 4732494 (Open Web Text)

Max Activating Token Index: 247

Text #18

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.5308. Min Act: -0.1700

Data Index: 5068440 (Open Web Text)

Max Activating Token Index: 724

Text #19

Max Range: 3.6436. Min Range: -3.6436

Max Act: 3.5194. Min Act: -0.1700

Data Index: 1475647 (Open Web Text)

Max Activating Token Index: 96