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

Dataset: Open Web Text

Neuron 2810 in Layer 3

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: 2.8369. Min Range: -2.8369

Max Act: 2.8224. Min Act: -0.1700

Data Index: 5351377 (Open Web Text)

Max Activating Token Index: 130

Text #1

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.8180. Min Act: -0.1700

Data Index: 1799633 (Open Web Text)

Max Activating Token Index: 238

Text #2

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.8369. Min Act: -0.1700

Data Index: 238376 (Open Web Text)

Max Activating Token Index: 28

Text #3

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.7882. Min Act: -0.1700

Data Index: 8661442 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.8052. Min Act: -0.1700

Data Index: 6995312 (Open Web Text)

Max Activating Token Index: 444

Text #5

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.7903. Min Act: -0.1700

Data Index: 8169917 (Open Web Text)

Max Activating Token Index: 11

Text #6

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.7902. Min Act: -0.1700

Data Index: 8254479 (Open Web Text)

Max Activating Token Index: 162

Text #7

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.7760. Min Act: -0.1700

Data Index: 96791 (Open Web Text)

Max Activating Token Index: 433

Text #8

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.7558. Min Act: -0.1700

Data Index: 328314 (Open Web Text)

Max Activating Token Index: 601

Text #9

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.7510. Min Act: -0.1700

Data Index: 8304368 (Open Web Text)

Max Activating Token Index: 729

Text #10

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.7855. Min Act: -0.1700

Data Index: 2422135 (Open Web Text)

Max Activating Token Index: 58

Text #11

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.7540. Min Act: -0.1700

Data Index: 856246 (Open Web Text)

Max Activating Token Index: 181

Text #12

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.7630. Min Act: -0.1700

Data Index: 1787476 (Open Web Text)

Max Activating Token Index: 264

Text #13

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.7620. Min Act: -0.1700

Data Index: 70057 (Open Web Text)

Max Activating Token Index: 533

Text #14

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.7510. Min Act: -0.1700

Data Index: 7534917 (Open Web Text)

Max Activating Token Index: 9

Text #15

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.7534. Min Act: -0.1700

Data Index: 4985007 (Open Web Text)

Max Activating Token Index: 780

Text #16

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.7495. Min Act: -0.1700

Data Index: 2107483 (Open Web Text)

Max Activating Token Index: 650

Text #17

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.7752. Min Act: -0.1700

Data Index: 1991027 (Open Web Text)

Max Activating Token Index: 729

Text #18

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.7292. Min Act: -0.1700

Data Index: 370506 (Open Web Text)

Max Activating Token Index: 54

Text #19

Max Range: 2.8369. Min Range: -2.8369

Max Act: 2.7337. Min Act: -0.1700

Data Index: 29969 (Open Web Text)

Max Activating Token Index: 35