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

Dataset: Open Web Text

Neuron 2997 in Layer 6

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: 5.1986. Min Range: -5.1986

Max Act: 5.1986. Min Act: -0.1700

Data Index: 5011414 (Open Web Text)

Max Activating Token Index: 390

Text #1

Max Range: 5.1986. Min Range: -5.1986

Max Act: 5.1792. Min Act: -0.1700

Data Index: 3367555 (Open Web Text)

Max Activating Token Index: 533

Text #2

Max Range: 5.1986. Min Range: -5.1986

Max Act: 5.0875. Min Act: -0.1700

Data Index: 2473797 (Open Web Text)

Max Activating Token Index: 885

Text #3

Max Range: 5.1986. Min Range: -5.1986

Max Act: 5.0159. Min Act: -0.1700

Data Index: 8214270 (Open Web Text)

Max Activating Token Index: 887

Text #4

Max Range: 5.1986. Min Range: -5.1986

Max Act: 4.9939. Min Act: -0.1700

Data Index: 6542152 (Open Web Text)

Max Activating Token Index: 390

Text #5

Max Range: 5.1986. Min Range: -5.1986

Max Act: 5.0349. Min Act: -0.1700

Data Index: 5857015 (Open Web Text)

Max Activating Token Index: 873

Text #6

Max Range: 5.1986. Min Range: -5.1986

Max Act: 4.9813. Min Act: -0.1700

Data Index: 7938022 (Open Web Text)

Max Activating Token Index: 372

Text #7

Max Range: 5.1986. Min Range: -5.1986

Max Act: 4.8778. Min Act: -0.1700

Data Index: 7842742 (Open Web Text)

Max Activating Token Index: 479

Text #8

Max Range: 5.1986. Min Range: -5.1986

Max Act: 4.9010. Min Act: -0.1700

Data Index: 4629834 (Open Web Text)

Max Activating Token Index: 425

Text #9

Max Range: 5.1986. Min Range: -5.1986

Max Act: 4.8575. Min Act: -0.1700

Data Index: 4295624 (Open Web Text)

Max Activating Token Index: 305

Text #10

Max Range: 5.1986. Min Range: -5.1986

Max Act: 4.8392. Min Act: -0.1700

Data Index: 6621083 (Open Web Text)

Max Activating Token Index: 114

Text #11

Max Range: 5.1986. Min Range: -5.1986

Max Act: 4.8210. Min Act: -0.1700

Data Index: 480606 (Open Web Text)

Max Activating Token Index: 701

Text #12

Max Range: 5.1986. Min Range: -5.1986

Max Act: 4.7778. Min Act: -0.1700

Data Index: 2929816 (Open Web Text)

Max Activating Token Index: 976

Text #13

Max Range: 5.1986. Min Range: -5.1986

Max Act: 4.7679. Min Act: -0.1700

Data Index: 5813124 (Open Web Text)

Max Activating Token Index: 820

Text #14

Max Range: 5.1986. Min Range: -5.1986

Max Act: 4.7514. Min Act: -0.1700

Data Index: 7361248 (Open Web Text)

Max Activating Token Index: 776

Text #15

Max Range: 5.1986. Min Range: -5.1986

Max Act: 4.7543. Min Act: -0.1700

Data Index: 4074284 (Open Web Text)

Max Activating Token Index: 408

Text #16

Max Range: 5.1986. Min Range: -5.1986

Max Act: 4.7842. Min Act: -0.1700

Data Index: 2278043 (Open Web Text)

Max Activating Token Index: 704

Text #17

Max Range: 5.1986. Min Range: -5.1986

Max Act: 4.7331. Min Act: -0.1700

Data Index: 3300424 (Open Web Text)

Max Activating Token Index: 427

Text #18

Max Range: 5.1986. Min Range: -5.1986

Max Act: 4.7392. Min Act: -0.1700

Data Index: 2349944 (Open Web Text)

Max Activating Token Index: 812

Text #19

Max Range: 5.1986. Min Range: -5.1986

Max Act: 4.7201. Min Act: -0.1700

Data Index: 760348 (Open Web Text)

Max Activating Token Index: 1010