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

Dataset: Open Web Text

Neuron 2121 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: 4.6249. Min Range: -4.6249

Max Act: 4.6249. Min Act: -0.1700

Data Index: 6795078 (Open Web Text)

Max Activating Token Index: 217

Text #1

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.4864. Min Act: -0.1700

Data Index: 222817 (Open Web Text)

Max Activating Token Index: 28

Text #2

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.4573. Min Act: -0.1700

Data Index: 3541870 (Open Web Text)

Max Activating Token Index: 302

Text #3

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.4367. Min Act: -0.1700

Data Index: 3206272 (Open Web Text)

Max Activating Token Index: 989

Text #4

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3999. Min Act: -0.1700

Data Index: 7236792 (Open Web Text)

Max Activating Token Index: 347

Text #5

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3853. Min Act: -0.1700

Data Index: 840780 (Open Web Text)

Max Activating Token Index: 220

Text #6

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3822. Min Act: -0.1700

Data Index: 642121 (Open Web Text)

Max Activating Token Index: 624

Text #7

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3762. Min Act: -0.1700

Data Index: 2185675 (Open Web Text)

Max Activating Token Index: 68

Text #8

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3438. Min Act: -0.1700

Data Index: 928525 (Open Web Text)

Max Activating Token Index: 583

Text #9

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3290. Min Act: -0.1700

Data Index: 5316769 (Open Web Text)

Max Activating Token Index: 416

Text #10

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3030. Min Act: -0.1700

Data Index: 7783624 (Open Web Text)

Max Activating Token Index: 656

Text #11

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3177. Min Act: -0.1700

Data Index: 3643984 (Open Web Text)

Max Activating Token Index: 13

Text #12

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.3405. Min Act: -0.1700

Data Index: 7059561 (Open Web Text)

Max Activating Token Index: 613

Text #13

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.2753. Min Act: -0.1700

Data Index: 5539385 (Open Web Text)

Max Activating Token Index: 83

Text #14

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.2676. Min Act: -0.1700

Data Index: 6162899 (Open Web Text)

Max Activating Token Index: 620

Text #15

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.2786. Min Act: -0.1700

Data Index: 3765104 (Open Web Text)

Max Activating Token Index: 141

Text #16

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.2287. Min Act: -0.1700

Data Index: 3987344 (Open Web Text)

Max Activating Token Index: 376

Text #17

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.2516. Min Act: -0.1700

Data Index: 971307 (Open Web Text)

Max Activating Token Index: 266

Text #18

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.2387. Min Act: -0.1700

Data Index: 3293189 (Open Web Text)

Max Activating Token Index: 728

Text #19

Max Range: 4.6249. Min Range: -4.6249

Max Act: 4.2585. Min Act: -0.1700

Data Index: 4643131 (Open Web Text)

Max Activating Token Index: 84