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

Dataset: Open Web Text

Neuron 190 in Layer 1

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: 4.3827. Min Range: -4.3827

Max Act: 4.3827. Min Act: -0.1700

Data Index: 5204213 (Open Web Text)

Max Activating Token Index: 208

Text #1

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.3811. Min Act: -0.1700

Data Index: 403808 (Open Web Text)

Max Activating Token Index: 82

Text #2

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.3363. Min Act: -0.1700

Data Index: 5569299 (Open Web Text)

Max Activating Token Index: 118

Text #3

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.3323. Min Act: -0.1700

Data Index: 8004082 (Open Web Text)

Max Activating Token Index: 431

Text #4

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.3049. Min Act: -0.1700

Data Index: 6022689 (Open Web Text)

Max Activating Token Index: 846

Text #5

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.2952. Min Act: -0.1700

Data Index: 1374177 (Open Web Text)

Max Activating Token Index: 692

Text #6

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.2973. Min Act: -0.1700

Data Index: 4849581 (Open Web Text)

Max Activating Token Index: 185

Text #7

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.2975. Min Act: -0.1700

Data Index: 7794405 (Open Web Text)

Max Activating Token Index: 683

Text #8

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.2967. Min Act: -0.1700

Data Index: 3947564 (Open Web Text)

Max Activating Token Index: 437

Text #9

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.3226. Min Act: -0.1700

Data Index: 6552197 (Open Web Text)

Max Activating Token Index: 374

Text #10

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.3038. Min Act: -0.1700

Data Index: 6362666 (Open Web Text)

Max Activating Token Index: 720

Text #11

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.3143. Min Act: -0.1700

Data Index: 1966918 (Open Web Text)

Max Activating Token Index: 158

Text #12

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.3245. Min Act: -0.1700

Data Index: 1842554 (Open Web Text)

Max Activating Token Index: 124

Text #13

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.3232. Min Act: -0.1700

Data Index: 1600908 (Open Web Text)

Max Activating Token Index: 143

Text #14

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.2868. Min Act: -0.1700

Data Index: 1409311 (Open Web Text)

Max Activating Token Index: 530

Text #15

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.2617. Min Act: -0.1700

Data Index: 2287657 (Open Web Text)

Max Activating Token Index: 130

Text #16

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.2848. Min Act: -0.1700

Data Index: 2330454 (Open Web Text)

Max Activating Token Index: 260

Text #17

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.2671. Min Act: -0.1700

Data Index: 4679685 (Open Web Text)

Max Activating Token Index: 235

Text #18

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.2752. Min Act: -0.1700

Data Index: 2417630 (Open Web Text)

Max Activating Token Index: 205

Text #19

Max Range: 4.3827. Min Range: -4.3827

Max Act: 4.2724. Min Act: -0.1700

Data Index: 5575364 (Open Web Text)

Max Activating Token Index: 167