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

Dataset: Open Web Text

Neuron 205 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: 3.5670. Min Range: -3.5670

Max Act: 3.5670. Min Act: -0.1700

Data Index: 4604788 (Open Web Text)

Max Activating Token Index: 351

Text #1

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.4326. Min Act: -0.1700

Data Index: 3882855 (Open Web Text)

Max Activating Token Index: 221

Text #2

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.4456. Min Act: -0.1700

Data Index: 8625163 (Open Web Text)

Max Activating Token Index: 502

Text #3

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.3977. Min Act: -0.1700

Data Index: 5278104 (Open Web Text)

Max Activating Token Index: 359

Text #4

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.4239. Min Act: -0.1700

Data Index: 4653665 (Open Web Text)

Max Activating Token Index: 949

Text #5

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.3597. Min Act: -0.1700

Data Index: 6344781 (Open Web Text)

Max Activating Token Index: 338

Text #6

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.3884. Min Act: -0.1700

Data Index: 5473123 (Open Web Text)

Max Activating Token Index: 222

Text #7

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.4276. Min Act: -0.1700

Data Index: 4245112 (Open Web Text)

Max Activating Token Index: 390

Text #8

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.3861. Min Act: -0.1700

Data Index: 2147901 (Open Web Text)

Max Activating Token Index: 496

Text #9

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.3609. Min Act: -0.1700

Data Index: 2649571 (Open Web Text)

Max Activating Token Index: 515

Text #10

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.3452. Min Act: -0.1700

Data Index: 2781455 (Open Web Text)

Max Activating Token Index: 115

Text #11

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.3492. Min Act: -0.1700

Data Index: 8633605 (Open Web Text)

Max Activating Token Index: 671

Text #12

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.3350. Min Act: -0.1700

Data Index: 8751570 (Open Web Text)

Max Activating Token Index: 502

Text #13

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.3773. Min Act: -0.1700

Data Index: 5508130 (Open Web Text)

Max Activating Token Index: 598

Text #14

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.3523. Min Act: -0.1700

Data Index: 5193881 (Open Web Text)

Max Activating Token Index: 697

Text #15

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.3440. Min Act: -0.1700

Data Index: 1718715 (Open Web Text)

Max Activating Token Index: 641

Text #16

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.3237. Min Act: -0.1700

Data Index: 4593568 (Open Web Text)

Max Activating Token Index: 656

Text #17

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.3506. Min Act: -0.1700

Data Index: 3231757 (Open Web Text)

Max Activating Token Index: 467

Text #18

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.3751. Min Act: -0.1700

Data Index: 4170493 (Open Web Text)

Max Activating Token Index: 727

Text #19

Max Range: 3.5670. Min Range: -3.5670

Max Act: 3.3227. Min Act: -0.1700

Data Index: 198818 (Open Web Text)

Max Activating Token Index: 855