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

Dataset: Open Web Text

Neuron 382 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: 2.6771. Min Range: -2.6771

Max Act: 2.6771. Min Act: -0.1700

Data Index: 5980639 (Open Web Text)

Max Activating Token Index: 485

Text #1

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.5858. Min Act: -0.1700

Data Index: 5337736 (Open Web Text)

Max Activating Token Index: 799

Text #2

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.6033. Min Act: -0.1700

Data Index: 4392550 (Open Web Text)

Max Activating Token Index: 162

Text #3

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.5493. Min Act: -0.1700

Data Index: 4689513 (Open Web Text)

Max Activating Token Index: 642

Text #4

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.5601. Min Act: -0.1700

Data Index: 6967650 (Open Web Text)

Max Activating Token Index: 358

Text #5

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.5587. Min Act: -0.1700

Data Index: 3416795 (Open Web Text)

Max Activating Token Index: 178

Text #6

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.5402. Min Act: -0.1700

Data Index: 962002 (Open Web Text)

Max Activating Token Index: 356

Text #7

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.5601. Min Act: -0.1700

Data Index: 3432895 (Open Web Text)

Max Activating Token Index: 843

Text #8

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.5518. Min Act: -0.1700

Data Index: 6306442 (Open Web Text)

Max Activating Token Index: 319

Text #9

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.5385. Min Act: -0.1700

Data Index: 7515676 (Open Web Text)

Max Activating Token Index: 361

Text #10

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.5478. Min Act: -0.1700

Data Index: 2237865 (Open Web Text)

Max Activating Token Index: 212

Text #11

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.5025. Min Act: -0.1700

Data Index: 7890642 (Open Web Text)

Max Activating Token Index: 792

Text #12

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.5019. Min Act: -0.1700

Data Index: 7886136 (Open Web Text)

Max Activating Token Index: 742

Text #13

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.5019. Min Act: -0.1700

Data Index: 2398327 (Open Web Text)

Max Activating Token Index: 396

Text #14

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.4802. Min Act: -0.1700

Data Index: 1098936 (Open Web Text)

Max Activating Token Index: 349

Text #15

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.4992. Min Act: -0.1700

Data Index: 1290340 (Open Web Text)

Max Activating Token Index: 650

Text #16

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.4804. Min Act: -0.1700

Data Index: 2358577 (Open Web Text)

Max Activating Token Index: 697

Text #17

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.4744. Min Act: -0.1700

Data Index: 3092141 (Open Web Text)

Max Activating Token Index: 252

Text #18

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.4818. Min Act: -0.1700

Data Index: 2123180 (Open Web Text)

Max Activating Token Index: 195

Text #19

Max Range: 2.6771. Min Range: -2.6771

Max Act: 2.4871. Min Act: -0.1700

Data Index: 737528 (Open Web Text)

Max Activating Token Index: 848