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

Dataset: Open Web Text

Neuron 1702 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: 4.5783. Min Range: -4.5783

Max Act: 4.5783. Min Act: -0.1700

Data Index: 2049543 (Open Web Text)

Max Activating Token Index: 462

Text #1

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.3676. Min Act: -0.1700

Data Index: 36304 (Open Web Text)

Max Activating Token Index: 184

Text #2

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.3892. Min Act: -0.1700

Data Index: 3510775 (Open Web Text)

Max Activating Token Index: 499

Text #3

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.3626. Min Act: -0.1700

Data Index: 7030029 (Open Web Text)

Max Activating Token Index: 636

Text #4

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.2898. Min Act: -0.1700

Data Index: 5316931 (Open Web Text)

Max Activating Token Index: 718

Text #5

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.3424. Min Act: -0.1700

Data Index: 8764523 (Open Web Text)

Max Activating Token Index: 668

Text #6

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.3138. Min Act: -0.1700

Data Index: 1467517 (Open Web Text)

Max Activating Token Index: 578

Text #7

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.3576. Min Act: -0.1700

Data Index: 8761315 (Open Web Text)

Max Activating Token Index: 319

Text #8

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.3333. Min Act: -0.1700

Data Index: 7442211 (Open Web Text)

Max Activating Token Index: 616

Text #9

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.2972. Min Act: -0.1700

Data Index: 4907213 (Open Web Text)

Max Activating Token Index: 705

Text #10

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.2658. Min Act: -0.1700

Data Index: 8643768 (Open Web Text)

Max Activating Token Index: 657

Text #11

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.2691. Min Act: -0.1700

Data Index: 3066662 (Open Web Text)

Max Activating Token Index: 540

Text #12

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.2489. Min Act: -0.1700

Data Index: 5587634 (Open Web Text)

Max Activating Token Index: 593

Text #13

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.2459. Min Act: -0.1700

Data Index: 5365125 (Open Web Text)

Max Activating Token Index: 102

Text #14

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.2308. Min Act: -0.1700

Data Index: 3287941 (Open Web Text)

Max Activating Token Index: 732

Text #15

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.2740. Min Act: -0.1700

Data Index: 5609688 (Open Web Text)

Max Activating Token Index: 208

Text #16

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.2355. Min Act: -0.1700

Data Index: 6342023 (Open Web Text)

Max Activating Token Index: 118

Text #17

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.2186. Min Act: -0.1700

Data Index: 4176415 (Open Web Text)

Max Activating Token Index: 583

Text #18

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.2231. Min Act: -0.1700

Data Index: 6648809 (Open Web Text)

Max Activating Token Index: 617

Text #19

Max Range: 4.5783. Min Range: -4.5783

Max Act: 4.2196. Min Act: -0.1700

Data Index: 7440182 (Open Web Text)

Max Activating Token Index: 622