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

Dataset: Open Web Text

Neuron 1188 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: 4.4632. Min Range: -4.4632

Max Act: 4.4632. Min Act: -0.1700

Data Index: 2939699 (Open Web Text)

Max Activating Token Index: 775

Text #1

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.3696. Min Act: -0.1700

Data Index: 2939701 (Open Web Text)

Max Activating Token Index: 250

Text #2

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.4076. Min Act: -0.1700

Data Index: 18131 (Open Web Text)

Max Activating Token Index: 411

Text #3

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.3933. Min Act: -0.1700

Data Index: 3790654 (Open Web Text)

Max Activating Token Index: 465

Text #4

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.3449. Min Act: -0.1700

Data Index: 6383576 (Open Web Text)

Max Activating Token Index: 715

Text #5

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.3152. Min Act: -0.1700

Data Index: 8655310 (Open Web Text)

Max Activating Token Index: 664

Text #6

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.2779. Min Act: -0.1700

Data Index: 319858 (Open Web Text)

Max Activating Token Index: 374

Text #7

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.2376. Min Act: -0.1700

Data Index: 4265189 (Open Web Text)

Max Activating Token Index: 397

Text #8

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.2405. Min Act: -0.1700

Data Index: 4821421 (Open Web Text)

Max Activating Token Index: 182

Text #9

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.2472. Min Act: -0.1700

Data Index: 8438553 (Open Web Text)

Max Activating Token Index: 366

Text #10

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.1850. Min Act: -0.1700

Data Index: 6872456 (Open Web Text)

Max Activating Token Index: 285

Text #11

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.3182. Min Act: -0.1700

Data Index: 5437174 (Open Web Text)

Max Activating Token Index: 543

Text #12

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.2508. Min Act: -0.1700

Data Index: 2230170 (Open Web Text)

Max Activating Token Index: 653

Text #13

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.2151. Min Act: -0.1700

Data Index: 2858301 (Open Web Text)

Max Activating Token Index: 242

Text #14

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.2074. Min Act: -0.1700

Data Index: 5135703 (Open Web Text)

Max Activating Token Index: 61

Text #15

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.2369. Min Act: -0.1700

Data Index: 4754450 (Open Web Text)

Max Activating Token Index: 661

Text #16

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.2415. Min Act: -0.1700

Data Index: 323340 (Open Web Text)

Max Activating Token Index: 780

Text #17

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.1572. Min Act: -0.1700

Data Index: 5623548 (Open Web Text)

Max Activating Token Index: 397

Text #18

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.1830. Min Act: -0.1700

Data Index: 8108611 (Open Web Text)

Max Activating Token Index: 799

Text #19

Max Range: 4.4632. Min Range: -4.4632

Max Act: 4.2045. Min Act: -0.1700

Data Index: 6735284 (Open Web Text)

Max Activating Token Index: 55