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

Dataset: Open Web Text

Neuron 1071 in Layer 6

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: 3.0935. Min Range: -3.0935

Max Act: 3.0935. Min Act: -0.1700

Data Index: 2933223 (Open Web Text)

Max Activating Token Index: 442

Text #1

Max Range: 3.0935. Min Range: -3.0935

Max Act: 3.0591. Min Act: -0.1700

Data Index: 6983768 (Open Web Text)

Max Activating Token Index: 149

Text #2

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.9502. Min Act: -0.1700

Data Index: 7294325 (Open Web Text)

Max Activating Token Index: 256

Text #3

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.9444. Min Act: -0.1700

Data Index: 6174049 (Open Web Text)

Max Activating Token Index: 245

Text #4

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.9265. Min Act: -0.1700

Data Index: 6109068 (Open Web Text)

Max Activating Token Index: 374

Text #5

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.9179. Min Act: -0.1700

Data Index: 5345359 (Open Web Text)

Max Activating Token Index: 119

Text #6

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.9188. Min Act: -0.1700

Data Index: 6438473 (Open Web Text)

Max Activating Token Index: 298

Text #7

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.9005. Min Act: -0.1700

Data Index: 279539 (Open Web Text)

Max Activating Token Index: 687

Text #8

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.8845. Min Act: -0.1700

Data Index: 6760803 (Open Web Text)

Max Activating Token Index: 763

Text #9

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.8667. Min Act: -0.1700

Data Index: 3500569 (Open Web Text)

Max Activating Token Index: 696

Text #10

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.8733. Min Act: -0.1700

Data Index: 8577461 (Open Web Text)

Max Activating Token Index: 180

Text #11

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.8801. Min Act: -0.1700

Data Index: 2495648 (Open Web Text)

Max Activating Token Index: 907

Text #12

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.8739. Min Act: -0.1700

Data Index: 2868877 (Open Web Text)

Max Activating Token Index: 618

Text #13

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.8435. Min Act: -0.1700

Data Index: 4297442 (Open Web Text)

Max Activating Token Index: 257

Text #14

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.8197. Min Act: -0.1700

Data Index: 1751346 (Open Web Text)

Max Activating Token Index: 923

Text #15

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.8459. Min Act: -0.1700

Data Index: 6084783 (Open Web Text)

Max Activating Token Index: 104

Text #16

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.8456. Min Act: -0.1700

Data Index: 6973937 (Open Web Text)

Max Activating Token Index: 680

Text #17

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.8319. Min Act: -0.1700

Data Index: 7301857 (Open Web Text)

Max Activating Token Index: 537

Text #18

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.8369. Min Act: -0.1700

Data Index: 4099882 (Open Web Text)

Max Activating Token Index: 623

Text #19

Max Range: 3.0935. Min Range: -3.0935

Max Act: 2.8210. Min Act: -0.1700

Data Index: 2878036 (Open Web Text)

Max Activating Token Index: 739