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

Dataset: Open Web Text

Neuron 1802 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: 3.3935. Min Range: -3.3935

Max Act: 3.3935. Min Act: -0.1700

Data Index: 3462079 (Open Web Text)

Max Activating Token Index: 918

Text #1

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.3555. Min Act: -0.1700

Data Index: 6703023 (Open Web Text)

Max Activating Token Index: 479

Text #2

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.3533. Min Act: -0.1700

Data Index: 513787 (Open Web Text)

Max Activating Token Index: 654

Text #3

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.3514. Min Act: -0.1700

Data Index: 2500040 (Open Web Text)

Max Activating Token Index: 459

Text #4

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.3331. Min Act: -0.1700

Data Index: 1209634 (Open Web Text)

Max Activating Token Index: 1014

Text #5

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.3112. Min Act: -0.1700

Data Index: 4163332 (Open Web Text)

Max Activating Token Index: 448

Text #6

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.3354. Min Act: -0.1700

Data Index: 8111736 (Open Web Text)

Max Activating Token Index: 50

Text #7

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.3399. Min Act: -0.1700

Data Index: 6068678 (Open Web Text)

Max Activating Token Index: 912

Text #8

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.3268. Min Act: -0.1700

Data Index: 3724789 (Open Web Text)

Max Activating Token Index: 297

Text #9

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.2749. Min Act: -0.1700

Data Index: 6865995 (Open Web Text)

Max Activating Token Index: 459

Text #10

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.3043. Min Act: -0.1700

Data Index: 7364782 (Open Web Text)

Max Activating Token Index: 833

Text #11

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.2708. Min Act: -0.1700

Data Index: 249879 (Open Web Text)

Max Activating Token Index: 976

Text #12

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.2939. Min Act: -0.1700

Data Index: 8363848 (Open Web Text)

Max Activating Token Index: 186

Text #13

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.2931. Min Act: -0.1700

Data Index: 1125768 (Open Web Text)

Max Activating Token Index: 286

Text #14

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.3043. Min Act: -0.1700

Data Index: 5199677 (Open Web Text)

Max Activating Token Index: 950

Text #15

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.2980. Min Act: -0.1700

Data Index: 4041002 (Open Web Text)

Max Activating Token Index: 408

Text #16

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.2865. Min Act: -0.1700

Data Index: 2137804 (Open Web Text)

Max Activating Token Index: 400

Text #17

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.2832. Min Act: -0.1700

Data Index: 7926758 (Open Web Text)

Max Activating Token Index: 785

Text #18

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.2713. Min Act: -0.1700

Data Index: 5852093 (Open Web Text)

Max Activating Token Index: 261

Text #19

Max Range: 3.3935. Min Range: -3.3935

Max Act: 3.2779. Min Act: -0.1700

Data Index: 398755 (Open Web Text)

Max Activating Token Index: 742