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

Dataset: Open Web Text

Neuron 944 in Layer 4

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: 3.6771. Min Range: -3.6771

Max Act: 3.6771. Min Act: -0.1700

Data Index: 6982066 (Open Web Text)

Max Activating Token Index: 924

Text #1

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.6692. Min Act: -0.1700

Data Index: 7764910 (Open Web Text)

Max Activating Token Index: 558

Text #2

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.6444. Min Act: -0.1700

Data Index: 6309452 (Open Web Text)

Max Activating Token Index: 794

Text #3

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.6179. Min Act: -0.1700

Data Index: 8502727 (Open Web Text)

Max Activating Token Index: 971

Text #4

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.6208. Min Act: -0.1700

Data Index: 4218270 (Open Web Text)

Max Activating Token Index: 293

Text #5

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.6015. Min Act: -0.1700

Data Index: 8230220 (Open Web Text)

Max Activating Token Index: 675

Text #6

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5634. Min Act: -0.1700

Data Index: 4284185 (Open Web Text)

Max Activating Token Index: 511

Text #7

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5477. Min Act: -0.1700

Data Index: 6408761 (Open Web Text)

Max Activating Token Index: 926

Text #8

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5919. Min Act: -0.1700

Data Index: 537619 (Open Web Text)

Max Activating Token Index: 239

Text #9

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5755. Min Act: -0.1700

Data Index: 6895191 (Open Web Text)

Max Activating Token Index: 816

Text #10

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5729. Min Act: -0.1700

Data Index: 3120122 (Open Web Text)

Max Activating Token Index: 231

Text #11

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5714. Min Act: -0.1700

Data Index: 3112029 (Open Web Text)

Max Activating Token Index: 137

Text #12

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5708. Min Act: -0.1700

Data Index: 6464295 (Open Web Text)

Max Activating Token Index: 760

Text #13

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5487. Min Act: -0.1700

Data Index: 2478688 (Open Web Text)

Max Activating Token Index: 371

Text #14

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5452. Min Act: -0.1700

Data Index: 1788527 (Open Web Text)

Max Activating Token Index: 612

Text #15

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5641. Min Act: -0.1700

Data Index: 1551662 (Open Web Text)

Max Activating Token Index: 856

Text #16

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5289. Min Act: -0.1700

Data Index: 6046313 (Open Web Text)

Max Activating Token Index: 613

Text #17

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5712. Min Act: -0.1700

Data Index: 2622955 (Open Web Text)

Max Activating Token Index: 588

Text #18

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5381. Min Act: -0.1700

Data Index: 4459081 (Open Web Text)

Max Activating Token Index: 639

Text #19

Max Range: 3.6771. Min Range: -3.6771

Max Act: 3.5415. Min Act: -0.1700

Data Index: 3340233 (Open Web Text)

Max Activating Token Index: 160