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

Dataset: Open Web Text

Neuron 793 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: 4.9388. Min Range: -4.9388

Max Act: 4.9388. Min Act: -0.1700

Data Index: 2424225 (Open Web Text)

Max Activating Token Index: 120

Text #1

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.8356. Min Act: -0.1700

Data Index: 2513513 (Open Web Text)

Max Activating Token Index: 877

Text #2

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.8213. Min Act: -0.1700

Data Index: 2620485 (Open Web Text)

Max Activating Token Index: 40

Text #3

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.8587. Min Act: -0.1700

Data Index: 5425197 (Open Web Text)

Max Activating Token Index: 445

Text #4

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.7975. Min Act: -0.1700

Data Index: 2900232 (Open Web Text)

Max Activating Token Index: 168

Text #5

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.8789. Min Act: -0.1700

Data Index: 2513511 (Open Web Text)

Max Activating Token Index: 535

Text #6

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.8314. Min Act: -0.1700

Data Index: 8373707 (Open Web Text)

Max Activating Token Index: 278

Text #7

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.7722. Min Act: -0.1700

Data Index: 5425200 (Open Web Text)

Max Activating Token Index: 367

Text #8

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.7735. Min Act: -0.1700

Data Index: 2842894 (Open Web Text)

Max Activating Token Index: 139

Text #9

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.7458. Min Act: -0.1700

Data Index: 6236817 (Open Web Text)

Max Activating Token Index: 246

Text #10

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.7144. Min Act: -0.1700

Data Index: 7047760 (Open Web Text)

Max Activating Token Index: 63

Text #11

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.7229. Min Act: -0.1700

Data Index: 814501 (Open Web Text)

Max Activating Token Index: 84

Text #12

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.7302. Min Act: -0.1700

Data Index: 5028079 (Open Web Text)

Max Activating Token Index: 792

Text #13

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.6838. Min Act: -0.1700

Data Index: 2383713 (Open Web Text)

Max Activating Token Index: 520

Text #14

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.6737. Min Act: -0.1700

Data Index: 6236816 (Open Web Text)

Max Activating Token Index: 336

Text #15

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.6883. Min Act: -0.1700

Data Index: 4447289 (Open Web Text)

Max Activating Token Index: 924

Text #16

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.6771. Min Act: -0.1700

Data Index: 4447291 (Open Web Text)

Max Activating Token Index: 75

Text #17

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.6277. Min Act: -0.1700

Data Index: 8501489 (Open Web Text)

Max Activating Token Index: 929

Text #18

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.6081. Min Act: -0.1700

Data Index: 2720890 (Open Web Text)

Max Activating Token Index: 328

Text #19

Max Range: 4.9388. Min Range: -4.9388

Max Act: 4.6194. Min Act: -0.1700

Data Index: 6034591 (Open Web Text)

Max Activating Token Index: 944