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

Dataset: Open Web Text

Neuron 698 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: 4.7366. Min Range: -4.7366

Max Act: 4.6900. Min Act: -0.1700

Data Index: 3463656 (Open Web Text)

Max Activating Token Index: 889

Text #1

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.7366. Min Act: -0.1700

Data Index: 6091464 (Open Web Text)

Max Activating Token Index: 993

Text #2

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.6755. Min Act: -0.1700

Data Index: 4231980 (Open Web Text)

Max Activating Token Index: 103

Text #3

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.6266. Min Act: -0.1700

Data Index: 6993164 (Open Web Text)

Max Activating Token Index: 105

Text #4

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.6274. Min Act: -0.1700

Data Index: 640789 (Open Web Text)

Max Activating Token Index: 1003

Text #5

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.6203. Min Act: -0.1700

Data Index: 3327961 (Open Web Text)

Max Activating Token Index: 606

Text #6

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.5840. Min Act: -0.1700

Data Index: 5815191 (Open Web Text)

Max Activating Token Index: 946

Text #7

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.5933. Min Act: -0.1700

Data Index: 5918037 (Open Web Text)

Max Activating Token Index: 607

Text #8

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.6312. Min Act: -0.1700

Data Index: 4119570 (Open Web Text)

Max Activating Token Index: 982

Text #9

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.5816. Min Act: -0.1700

Data Index: 4779792 (Open Web Text)

Max Activating Token Index: 616

Text #10

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.5415. Min Act: -0.1700

Data Index: 636632 (Open Web Text)

Max Activating Token Index: 488

Text #11

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.5703. Min Act: -0.1700

Data Index: 4231978 (Open Web Text)

Max Activating Token Index: 805

Text #12

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.5684. Min Act: -0.1700

Data Index: 1404708 (Open Web Text)

Max Activating Token Index: 583

Text #13

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.5627. Min Act: -0.1700

Data Index: 5855153 (Open Web Text)

Max Activating Token Index: 607

Text #14

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.5978. Min Act: -0.1700

Data Index: 3789025 (Open Web Text)

Max Activating Token Index: 642

Text #15

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.5780. Min Act: -0.1700

Data Index: 5402878 (Open Web Text)

Max Activating Token Index: 590

Text #16

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.5671. Min Act: -0.1700

Data Index: 5389562 (Open Web Text)

Max Activating Token Index: 541

Text #17

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.5370. Min Act: -0.1700

Data Index: 5276582 (Open Web Text)

Max Activating Token Index: 987

Text #18

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.5331. Min Act: -0.1700

Data Index: 218955 (Open Web Text)

Max Activating Token Index: 766

Text #19

Max Range: 4.7366. Min Range: -4.7366

Max Act: 4.5500. Min Act: -0.1700

Data Index: 4304778 (Open Web Text)

Max Activating Token Index: 286