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

Dataset: Open Web Text

Neuron 2654 in Layer 4

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: 5.6845. Min Range: -5.6845

Max Act: 5.6845. Min Act: -0.1700

Data Index: 6791143 (Open Web Text)

Max Activating Token Index: 608

Text #1

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.6619. Min Act: -0.1700

Data Index: 2684209 (Open Web Text)

Max Activating Token Index: 301

Text #2

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.6437. Min Act: -0.1700

Data Index: 3683612 (Open Web Text)

Max Activating Token Index: 221

Text #3

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.6410. Min Act: -0.1700

Data Index: 496200 (Open Web Text)

Max Activating Token Index: 687

Text #4

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.6130. Min Act: -0.1700

Data Index: 5775522 (Open Web Text)

Max Activating Token Index: 669

Text #5

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.5743. Min Act: -0.1700

Data Index: 7135122 (Open Web Text)

Max Activating Token Index: 661

Text #6

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.5581. Min Act: -0.1700

Data Index: 8594445 (Open Web Text)

Max Activating Token Index: 569

Text #7

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.5261. Min Act: -0.1700

Data Index: 571313 (Open Web Text)

Max Activating Token Index: 142

Text #8

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.4120. Min Act: -0.1700

Data Index: 3158219 (Open Web Text)

Max Activating Token Index: 228

Text #9

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.4674. Min Act: -0.1700

Data Index: 5624852 (Open Web Text)

Max Activating Token Index: 426

Text #10

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.4230. Min Act: -0.1700

Data Index: 4525050 (Open Web Text)

Max Activating Token Index: 615

Text #11

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.3872. Min Act: -0.1700

Data Index: 536515 (Open Web Text)

Max Activating Token Index: 266

Text #12

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.3711. Min Act: -0.1700

Data Index: 7826249 (Open Web Text)

Max Activating Token Index: 775

Text #13

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.3836. Min Act: -0.1700

Data Index: 6349521 (Open Web Text)

Max Activating Token Index: 479

Text #14

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.3514. Min Act: -0.1700

Data Index: 310891 (Open Web Text)

Max Activating Token Index: 452

Text #15

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.3665. Min Act: -0.1700

Data Index: 4508430 (Open Web Text)

Max Activating Token Index: 757

Text #16

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.3626. Min Act: -0.1700

Data Index: 8214934 (Open Web Text)

Max Activating Token Index: 379

Text #17

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.2993. Min Act: -0.1700

Data Index: 2000683 (Open Web Text)

Max Activating Token Index: 912

Text #18

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.3361. Min Act: -0.1700

Data Index: 3339019 (Open Web Text)

Max Activating Token Index: 566

Text #19

Max Range: 5.6845. Min Range: -5.6845

Max Act: 5.3162. Min Act: -0.1700

Data Index: 5023064 (Open Web Text)

Max Activating Token Index: 501