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

Dataset: Open Web Text

Neuron 2739 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: 4.4200. Min Range: -4.4200

Max Act: 4.4200. Min Act: -0.1700

Data Index: 7050509 (Open Web Text)

Max Activating Token Index: 26

Text #1

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.3480. Min Act: -0.1700

Data Index: 7184907 (Open Web Text)

Max Activating Token Index: 873

Text #2

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.3207. Min Act: -0.1700

Data Index: 2173017 (Open Web Text)

Max Activating Token Index: 33

Text #3

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.3187. Min Act: -0.1700

Data Index: 4675843 (Open Web Text)

Max Activating Token Index: 303

Text #4

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2804. Min Act: -0.1700

Data Index: 793216 (Open Web Text)

Max Activating Token Index: 61

Text #5

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.3223. Min Act: -0.1700

Data Index: 7980641 (Open Web Text)

Max Activating Token Index: 524

Text #6

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2699. Min Act: -0.1700

Data Index: 2920960 (Open Web Text)

Max Activating Token Index: 908

Text #7

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.3128. Min Act: -0.1700

Data Index: 2839207 (Open Web Text)

Max Activating Token Index: 88

Text #8

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.3242. Min Act: -0.1700

Data Index: 2154806 (Open Web Text)

Max Activating Token Index: 529

Text #9

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2785. Min Act: -0.1700

Data Index: 1124028 (Open Web Text)

Max Activating Token Index: 537

Text #10

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2902. Min Act: -0.1700

Data Index: 5894191 (Open Web Text)

Max Activating Token Index: 418

Text #11

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2873. Min Act: -0.1700

Data Index: 8561350 (Open Web Text)

Max Activating Token Index: 293

Text #12

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2968. Min Act: -0.1700

Data Index: 8354402 (Open Web Text)

Max Activating Token Index: 637

Text #13

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2569. Min Act: -0.1700

Data Index: 1985983 (Open Web Text)

Max Activating Token Index: 238

Text #14

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2715. Min Act: -0.1700

Data Index: 5969916 (Open Web Text)

Max Activating Token Index: 351

Text #15

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2568. Min Act: -0.1700

Data Index: 5158849 (Open Web Text)

Max Activating Token Index: 29

Text #16

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2278. Min Act: -0.1700

Data Index: 4071814 (Open Web Text)

Max Activating Token Index: 558

Text #17

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2422. Min Act: -0.1700

Data Index: 2567075 (Open Web Text)

Max Activating Token Index: 384

Text #18

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2482. Min Act: -0.1700

Data Index: 3959927 (Open Web Text)

Max Activating Token Index: 14

Text #19

Max Range: 4.4200. Min Range: -4.4200

Max Act: 4.2369. Min Act: -0.1700

Data Index: 6368199 (Open Web Text)

Max Activating Token Index: 114