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

Dataset: Open Web Text

Neuron 324 in Layer 5

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: 4.0652. Min Range: -4.0652

Max Act: 4.0652. Min Act: -0.1700

Data Index: 8096560 (Open Web Text)

Max Activating Token Index: 567

Text #1

Max Range: 4.0652. Min Range: -4.0652

Max Act: 4.0414. Min Act: -0.1700

Data Index: 2388854 (Open Web Text)

Max Activating Token Index: 337

Text #2

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.9581. Min Act: -0.1700

Data Index: 1926407 (Open Web Text)

Max Activating Token Index: 666

Text #3

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.9546. Min Act: -0.1700

Data Index: 6525353 (Open Web Text)

Max Activating Token Index: 654

Text #4

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.9498. Min Act: -0.1700

Data Index: 5787675 (Open Web Text)

Max Activating Token Index: 380

Text #5

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.9308. Min Act: -0.1700

Data Index: 2188008 (Open Web Text)

Max Activating Token Index: 374

Text #6

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.9159. Min Act: -0.1700

Data Index: 1317322 (Open Web Text)

Max Activating Token Index: 747

Text #7

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.9127. Min Act: -0.1700

Data Index: 470617 (Open Web Text)

Max Activating Token Index: 851

Text #8

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.8783. Min Act: -0.1700

Data Index: 2751040 (Open Web Text)

Max Activating Token Index: 127

Text #9

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.8458. Min Act: -0.1700

Data Index: 5109338 (Open Web Text)

Max Activating Token Index: 899

Text #10

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.8213. Min Act: -0.1700

Data Index: 2395521 (Open Web Text)

Max Activating Token Index: 926

Text #11

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.9006. Min Act: -0.1700

Data Index: 3071160 (Open Web Text)

Max Activating Token Index: 175

Text #12

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.8522. Min Act: -0.1700

Data Index: 4138822 (Open Web Text)

Max Activating Token Index: 522

Text #13

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.8306. Min Act: -0.1700

Data Index: 855708 (Open Web Text)

Max Activating Token Index: 183

Text #14

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.7940. Min Act: -0.1700

Data Index: 8116971 (Open Web Text)

Max Activating Token Index: 128

Text #15

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.8409. Min Act: -0.1700

Data Index: 8453651 (Open Web Text)

Max Activating Token Index: 805

Text #16

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.8274. Min Act: -0.1700

Data Index: 5080383 (Open Web Text)

Max Activating Token Index: 961

Text #17

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.7863. Min Act: -0.1700

Data Index: 5264404 (Open Web Text)

Max Activating Token Index: 754

Text #18

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.7698. Min Act: -0.1700

Data Index: 4804434 (Open Web Text)

Max Activating Token Index: 92

Text #19

Max Range: 4.0652. Min Range: -4.0652

Max Act: 3.7429. Min Act: -0.1700

Data Index: 3445186 (Open Web Text)

Max Activating Token Index: 862