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

Dataset: Open Web Text

Neuron 2327 in Layer 5

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: 4.7888. Min Range: -4.7888

Max Act: 4.7888. Min Act: -0.1700

Data Index: 1220645 (Open Web Text)

Max Activating Token Index: 974

Text #1

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.6256. Min Act: -0.1700

Data Index: 206559 (Open Web Text)

Max Activating Token Index: 906

Text #2

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.6037. Min Act: -0.1700

Data Index: 5501492 (Open Web Text)

Max Activating Token Index: 420

Text #3

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.5929. Min Act: -0.1700

Data Index: 1232647 (Open Web Text)

Max Activating Token Index: 523

Text #4

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.5571. Min Act: -0.1700

Data Index: 5807818 (Open Web Text)

Max Activating Token Index: 253

Text #5

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.5507. Min Act: -0.1700

Data Index: 2577599 (Open Web Text)

Max Activating Token Index: 376

Text #6

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.5587. Min Act: -0.1700

Data Index: 6062846 (Open Web Text)

Max Activating Token Index: 737

Text #7

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.5180. Min Act: -0.1700

Data Index: 2264382 (Open Web Text)

Max Activating Token Index: 993

Text #8

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.5279. Min Act: -0.1700

Data Index: 5013819 (Open Web Text)

Max Activating Token Index: 623

Text #9

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.4948. Min Act: -0.1700

Data Index: 2222554 (Open Web Text)

Max Activating Token Index: 546

Text #10

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.5130. Min Act: -0.1700

Data Index: 3039703 (Open Web Text)

Max Activating Token Index: 650

Text #11

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.4678. Min Act: -0.1700

Data Index: 1080599 (Open Web Text)

Max Activating Token Index: 786

Text #12

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.4664. Min Act: -0.1700

Data Index: 5523902 (Open Web Text)

Max Activating Token Index: 290

Text #13

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.4941. Min Act: -0.1700

Data Index: 3658701 (Open Web Text)

Max Activating Token Index: 75

Text #14

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.4692. Min Act: -0.1700

Data Index: 1132831 (Open Web Text)

Max Activating Token Index: 214

Text #15

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.4732. Min Act: -0.1700

Data Index: 7209877 (Open Web Text)

Max Activating Token Index: 748

Text #16

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.4672. Min Act: -0.1700

Data Index: 1780109 (Open Web Text)

Max Activating Token Index: 438

Text #17

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.5110. Min Act: -0.1700

Data Index: 4683559 (Open Web Text)

Max Activating Token Index: 962

Text #18

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.4427. Min Act: -0.1700

Data Index: 1197391 (Open Web Text)

Max Activating Token Index: 129

Text #19

Max Range: 4.7888. Min Range: -4.7888

Max Act: 4.4580. Min Act: -0.1700

Data Index: 2361722 (Open Web Text)

Max Activating Token Index: 685