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

Dataset: Open Web Text

Neuron 164 in Layer 2

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: 3.8263. Min Range: -3.8263

Max Act: 3.8263. Min Act: -0.1700

Data Index: 6605612 (Open Web Text)

Max Activating Token Index: 52

Text #1

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.5923. Min Act: -0.1700

Data Index: 81928 (Open Web Text)

Max Activating Token Index: 265

Text #2

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.5373. Min Act: -0.1700

Data Index: 2112011 (Open Web Text)

Max Activating Token Index: 702

Text #3

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.5220. Min Act: -0.1700

Data Index: 7070465 (Open Web Text)

Max Activating Token Index: 790

Text #4

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.5480. Min Act: -0.1700

Data Index: 3369607 (Open Web Text)

Max Activating Token Index: 728

Text #5

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.5251. Min Act: -0.1700

Data Index: 2306612 (Open Web Text)

Max Activating Token Index: 245

Text #6

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.5003. Min Act: -0.1700

Data Index: 5786168 (Open Web Text)

Max Activating Token Index: 498

Text #7

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.5152. Min Act: -0.1700

Data Index: 6701892 (Open Web Text)

Max Activating Token Index: 45

Text #8

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.5085. Min Act: -0.1700

Data Index: 3707653 (Open Web Text)

Max Activating Token Index: 297

Text #9

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.4900. Min Act: -0.1700

Data Index: 20408 (Open Web Text)

Max Activating Token Index: 197

Text #10

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.4786. Min Act: -0.1700

Data Index: 8181335 (Open Web Text)

Max Activating Token Index: 537

Text #11

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.4569. Min Act: -0.1700

Data Index: 2332861 (Open Web Text)

Max Activating Token Index: 304

Text #12

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.4501. Min Act: -0.1700

Data Index: 273744 (Open Web Text)

Max Activating Token Index: 20

Text #13

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.4373. Min Act: -0.1700

Data Index: 5505563 (Open Web Text)

Max Activating Token Index: 188

Text #14

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.4531. Min Act: -0.1700

Data Index: 7056493 (Open Web Text)

Max Activating Token Index: 113

Text #15

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.4494. Min Act: -0.1700

Data Index: 4696449 (Open Web Text)

Max Activating Token Index: 125

Text #16

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.4303. Min Act: -0.1700

Data Index: 549957 (Open Web Text)

Max Activating Token Index: 677

Text #17

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.4426. Min Act: -0.1700

Data Index: 4784791 (Open Web Text)

Max Activating Token Index: 853

Text #18

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.4262. Min Act: -0.1700

Data Index: 2701648 (Open Web Text)

Max Activating Token Index: 553

Text #19

Max Range: 3.8263. Min Range: -3.8263

Max Act: 3.4371. Min Act: -0.1700

Data Index: 4436140 (Open Web Text)

Max Activating Token Index: 892