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

Dataset: Open Web Text

Neuron 1345 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: 3.0414. Min Range: -3.0414

Max Act: 3.0414. Min Act: -0.1700

Data Index: 8569478 (Open Web Text)

Max Activating Token Index: 765

Text #1

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.9743. Min Act: -0.1700

Data Index: 5804140 (Open Web Text)

Max Activating Token Index: 1012

Text #2

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.9439. Min Act: -0.1700

Data Index: 864720 (Open Web Text)

Max Activating Token Index: 758

Text #3

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.9331. Min Act: -0.1700

Data Index: 7602898 (Open Web Text)

Max Activating Token Index: 894

Text #4

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8909. Min Act: -0.1700

Data Index: 3943764 (Open Web Text)

Max Activating Token Index: 588

Text #5

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8943. Min Act: -0.1700

Data Index: 2606479 (Open Web Text)

Max Activating Token Index: 385

Text #6

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.9032. Min Act: -0.1700

Data Index: 6848103 (Open Web Text)

Max Activating Token Index: 306

Text #7

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.9095. Min Act: -0.1700

Data Index: 7064706 (Open Web Text)

Max Activating Token Index: 669

Text #8

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8953. Min Act: -0.1700

Data Index: 7167508 (Open Web Text)

Max Activating Token Index: 894

Text #9

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8738. Min Act: -0.1700

Data Index: 857822 (Open Web Text)

Max Activating Token Index: 315

Text #10

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8655. Min Act: -0.1700

Data Index: 3767359 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8648. Min Act: -0.1700

Data Index: 8183158 (Open Web Text)

Max Activating Token Index: 664

Text #12

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8632. Min Act: -0.1700

Data Index: 3670499 (Open Web Text)

Max Activating Token Index: 138

Text #13

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8670. Min Act: -0.1700

Data Index: 3104011 (Open Web Text)

Max Activating Token Index: 73

Text #14

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8655. Min Act: -0.1700

Data Index: 358047 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8478. Min Act: -0.1700

Data Index: 782479 (Open Web Text)

Max Activating Token Index: 811

Text #16

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8219. Min Act: -0.1700

Data Index: 6599560 (Open Web Text)

Max Activating Token Index: 458

Text #17

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8469. Min Act: -0.1700

Data Index: 5366283 (Open Web Text)

Max Activating Token Index: 641

Text #18

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8416. Min Act: -0.1700

Data Index: 8240636 (Open Web Text)

Max Activating Token Index: 975

Text #19

Max Range: 3.0414. Min Range: -3.0414

Max Act: 2.8581. Min Act: -0.1700

Data Index: 83639 (Open Web Text)

Max Activating Token Index: 585