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

Dataset: Open Web Text

Neuron 2846 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: 5.0013. Min Range: -5.0013

Max Act: 5.0013. Min Act: -0.1700

Data Index: 7380823 (Open Web Text)

Max Activating Token Index: 29

Text #1

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.9424. Min Act: -0.1700

Data Index: 7370743 (Open Web Text)

Max Activating Token Index: 14

Text #2

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.9275. Min Act: -0.1700

Data Index: 7066485 (Open Web Text)

Max Activating Token Index: 534

Text #3

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.8395. Min Act: -0.1700

Data Index: 3045285 (Open Web Text)

Max Activating Token Index: 1022

Text #4

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.8543. Min Act: -0.1700

Data Index: 8298123 (Open Web Text)

Max Activating Token Index: 16

Text #5

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.8652. Min Act: -0.1700

Data Index: 8551038 (Open Web Text)

Max Activating Token Index: 49

Text #6

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.8214. Min Act: -0.1700

Data Index: 4227080 (Open Web Text)

Max Activating Token Index: 989

Text #7

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.8184. Min Act: -0.1700

Data Index: 5122915 (Open Web Text)

Max Activating Token Index: 661

Text #8

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.7883. Min Act: -0.1700

Data Index: 2465511 (Open Web Text)

Max Activating Token Index: 51

Text #9

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.7837. Min Act: -0.1700

Data Index: 265200 (Open Web Text)

Max Activating Token Index: 93

Text #10

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.7979. Min Act: -0.1700

Data Index: 142769 (Open Web Text)

Max Activating Token Index: 75

Text #11

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.7484. Min Act: -0.1700

Data Index: 8695187 (Open Web Text)

Max Activating Token Index: 970

Text #12

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.7278. Min Act: -0.1700

Data Index: 1843171 (Open Web Text)

Max Activating Token Index: 96

Text #13

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.7389. Min Act: -0.1700

Data Index: 6262500 (Open Web Text)

Max Activating Token Index: 906

Text #14

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.7378. Min Act: -0.1700

Data Index: 8134436 (Open Web Text)

Max Activating Token Index: 878

Text #15

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.7299. Min Act: -0.1700

Data Index: 7760306 (Open Web Text)

Max Activating Token Index: 623

Text #16

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.7593. Min Act: -0.1700

Data Index: 4586416 (Open Web Text)

Max Activating Token Index: 818

Text #17

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.7610. Min Act: -0.1700

Data Index: 4612663 (Open Web Text)

Max Activating Token Index: 128

Text #18

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.7451. Min Act: -0.1700

Data Index: 2194201 (Open Web Text)

Max Activating Token Index: 459

Text #19

Max Range: 5.0013. Min Range: -5.0013

Max Act: 4.7278. Min Act: -0.1700

Data Index: 2306260 (Open Web Text)

Max Activating Token Index: 459